Merge tag 'mvebu' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc

Pull ARM SoC updates for Marvell mvebu/kirkwood from Olof Johansson:
 "This is a branch with updates for Marvell's mvebu/kirkwood platforms.
  They came in late-ish, and were heavily interdependent such that it
  didn't make sense to split them up across the cross-platform topic
  branches.  So here they are (for the second release in a row) in a
  branch on their own."

* tag 'mvebu' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (88 commits)
  arm: l2x0: add aurora related properties to OF binding
  arm: mvebu: add Aurora L2 Cache Controller to the DT
  arm: mvebu: add L2 cache support
  dma: mv_xor: fix error handling path
  dma: mv_xor: fix error checking of irq_of_parse_and_map()
  dma: mv_xor: use request_irq() instead of devm_request_irq()
  dma: mv_xor: clear the window override control registers
  arm: mvebu: fix address decoding armada_cfg_base() function
  ARM: mvebu: update defconfig with I2C and RTC support
  ARM: mvebu: Add SATA support for OpenBlocks AX3-4
  ARM: mvebu: Add support for the RTC in OpenBlocks AX3-4
  ARM: mvebu: Add support for I2C on OpenBlocks AX3-4
  ARM: mvebu: Add support for I2C controllers in Armada 370/XP
  arm: mvebu: Add hardware I/O Coherency support
  arm: plat-orion: Add coherency attribute when setup mbus target
  arm: dma mapping: Export a dma ops function arm_dma_set_mask
  arm: mvebu: Add SMP support for Armada XP
  arm: mm: Add support for PJ4B cpu and init routines
  arm: mvebu: Add IPI support via doorbells
  arm: mvebu: Add initial support for power managmement service unit
  ...

76 files changed, 6530 insertions, 414 deletions

diff --git a/Documentation/devicetree/bindings/arm/armada-370-xp-mpic.txt b/Documentation/devicetree/bindings/arm/armada-370-xp-mpic.txt
index 70c0dc5..61df564 100644
--- a/Documentation/devicetree/bindings/arm/armada-370-xp-mpic.txt
+++ b/Documentation/devicetree/bindings/arm/armada-370-xp-mpic.txt
@@ -6,9 +6,15 @@ Required properties:
 - interrupt-controller: Identifies the node as an interrupt controller.
 - #interrupt-cells: The number of cells to define the interrupts. Should be 1.
   The cell is the IRQ number
+
 - reg: Should contain PMIC registers location and length. First pair
   for the main interrupt registers, second pair for the per-CPU
-  interrupt registers
+  interrupt registers. For this last pair, to be compliant with SMP
+  support, the "virtual" must be use (For the record, these registers
+  automatically map to the interrupt controller registers of the
+  current CPU)
+
+
 
 Example:
 
@@ -18,6 +24,6 @@ Example:
               #address-cells = <1>;
               #size-cells = <1>;
               interrupt-controller;
-              reg = <0xd0020000 0x1000>,
-                    <0xd0021000 0x1000>;
+              reg = <0xd0020a00 0x1d0>,
+                    <0xd0021070 0x58>;
         };
diff --git a/Documentation/devicetree/bindings/arm/armada-370-xp-pmsu.txt b/Documentation/devicetree/bindings/arm/armada-370-xp-pmsu.txt
new file mode 100644
index 0000000..926b4d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/armada-370-xp-pmsu.txt
@@ -0,0 +1,20 @@
+Power Management Service Unit(PMSU)
+-----------------------------------
+Available on Marvell SOCs: Armada 370 and Armada XP
+
+Required properties:
+
+- compatible: "marvell,armada-370-xp-pmsu"
+
+- reg: Should contain PMSU registers location and length. First pair
+  for the per-CPU SW Reset Control registers, second pair for the
+  Power Management Service Unit.
+
+Example:
+
+armada-370-xp-pmsu@d0022000 {
+	compatible = "marvell,armada-370-xp-pmsu";
+	reg = <0xd0022100 0x430>,
+	      <0xd0020800 0x20>;
+};
+
diff --git a/Documentation/devicetree/bindings/arm/armada-370-xp-timer.txt b/Documentation/devicetree/bindings/arm/armada-370-xp-timer.txt
index 8b6ea22..6483011 100644
--- a/Documentation/devicetree/bindings/arm/armada-370-xp-timer.txt
+++ b/Documentation/devicetree/bindings/arm/armada-370-xp-timer.txt
@@ -5,6 +5,7 @@ Required properties:
 - compatible: Should be "marvell,armada-370-xp-timer"
 - interrupts: Should contain the list of Global Timer interrupts
 - reg: Should contain the base address of the Global Timer registers
+- clocks: clock driving the timer hardware
 
 Optional properties:
 - marvell,timer-25Mhz: Tells whether the Global timer supports the 25
diff --git a/Documentation/devicetree/bindings/arm/coherency-fabric.txt b/Documentation/devicetree/bindings/arm/coherency-fabric.txt
new file mode 100644
index 0000000..17d8cd1
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/coherency-fabric.txt
@@ -0,0 +1,21 @@
+Coherency fabric
+----------------
+Available on Marvell SOCs: Armada 370 and Armada XP
+
+Required properties:
+
+- compatible: "marvell,coherency-fabric"
+
+- reg: Should contain coherency fabric registers location and
+  length. First pair for the coherency fabric registers, second pair
+  for the per-CPU fabric registers registers.
+
+Example:
+
+coherency-fabric@d0020200 {
+	compatible = "marvell,coherency-fabric";
+	reg = <0xd0020200 0xb0>,
+		<0xd0021810 0x1c>;
+
+};
+
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
index 7c3ee3a..cbef09b 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -10,6 +10,12 @@ Required properties:
 	"arm,pl310-cache"
 	"arm,l220-cache"
 	"arm,l210-cache"
+	"marvell,aurora-system-cache": Marvell Controller designed to be
+     compatible with the ARM one, with system cache mode (meaning
+     maintenance operations on L1 are broadcasted to the L2 and L2
+     performs the same operation).
+	"marvell,"aurora-outer-cache: Marvell Controller designed to be
+	 compatible with the ARM one with outer cache mode.
 - cache-unified : Specifies the cache is a unified cache.
 - cache-level : Should be set to 2 for a level 2 cache.
 - reg : Physical base address and size of cache controller's memory mapped
@@ -29,6 +35,9 @@ Optional properties:
   filter. Addresses in the filter window are directed to the M1 port. Other
   addresses will go to the M0 port.
 - interrupts : 1 combined interrupt.
+- cache-id-part: cache id part number to be used if it is not present
+  on hardware
+- wt-override: If present then L2 is forced to Write through mode
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/clock/mvebu-core-clock.txt b/Documentation/devicetree/bindings/clock/mvebu-core-clock.txt
new file mode 100644
index 0000000..1e66294
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/mvebu-core-clock.txt
@@ -0,0 +1,47 @@
+* Core Clock bindings for Marvell MVEBU SoCs
+
+Marvell MVEBU SoCs usually allow to determine core clock frequencies by
+reading the Sample-At-Reset (SAR) register. The core clock consumer should
+specify the desired clock by having the clock ID in its "clocks" phandle cell.
+
+The following is a list of provided IDs and clock names on Armada 370/XP:
+ 0 = tclk    (Internal Bus clock)
+ 1 = cpuclk  (CPU clock)
+ 2 = nbclk   (L2 Cache clock)
+ 3 = hclk    (DRAM control clock)
+ 4 = dramclk (DDR clock)
+
+The following is a list of provided IDs and clock names on Kirkwood and Dove:
+ 0 = tclk   (Internal Bus clock)
+ 1 = cpuclk (CPU0 clock)
+ 2 = l2clk  (L2 Cache clock derived from CPU0 clock)
+ 3 = ddrclk (DDR controller clock derived from CPU0 clock)
+
+Required properties:
+- compatible : shall be one of the following:
+	"marvell,armada-370-core-clock" - For Armada 370 SoC core clocks
+	"marvell,armada-xp-core-clock" - For Armada XP SoC core clocks
+	"marvell,dove-core-clock" - for Dove SoC core clocks
+	"marvell,kirkwood-core-clock" - for Kirkwood SoC (except mv88f6180)
+	"marvell,mv88f6180-core-clock" - for Kirkwood MV88f6180 SoC
+- reg : shall be the register address of the Sample-At-Reset (SAR) register
+- #clock-cells : from common clock binding; shall be set to 1
+
+Optional properties:
+- clock-output-names : from common clock binding; allows overwrite default clock
+	output names ("tclk", "cpuclk", "l2clk", "ddrclk")
+
+Example:
+
+core_clk: core-clocks@d0214 {
+	compatible = "marvell,dove-core-clock";
+	reg = <0xd0214 0x4>;
+	#clock-cells = <1>;
+};
+
+spi0: spi@10600 {
+	compatible = "marvell,orion-spi";
+	/* ... */
+	/* get tclk from core clock provider */
+	clocks = <&core_clk 0>;
+};
diff --git a/Documentation/devicetree/bindings/clock/mvebu-cpu-clock.txt b/Documentation/devicetree/bindings/clock/mvebu-cpu-clock.txt
new file mode 100644
index 0000000..feb8301
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/mvebu-cpu-clock.txt
@@ -0,0 +1,21 @@
+Device Tree Clock bindings for cpu clock of Marvell EBU platforms
+
+Required properties:
+- compatible : shall be one of the following:
+	"marvell,armada-xp-cpu-clock" - cpu clocks for Armada XP
+- reg : Address and length of the clock complex register set
+- #clock-cells : should be set to 1.
+- clocks : shall be the input parent clock phandle for the clock.
+
+cpuclk: clock-complex@d0018700 {
+	#clock-cells = <1>;
+	compatible = "marvell,armada-xp-cpu-clock";
+	reg = <0xd0018700 0xA0>;
+	clocks = <&coreclk 1>;
+}
+
+cpu@0 {
+	compatible = "marvell,sheeva-v7";
+	reg = <0>;
+	clocks = <&cpuclk 0>;
+};
diff --git a/Documentation/devicetree/bindings/clock/mvebu-gated-clock.txt b/Documentation/devicetree/bindings/clock/mvebu-gated-clock.txt
new file mode 100644
index 0000000..7337005
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/mvebu-gated-clock.txt
@@ -0,0 +1,119 @@
+* Gated Clock bindings for Marvell Orion SoCs
+
+Marvell Dove and Kirkwood allow some peripheral clocks to be gated to save
+some power. The clock consumer should specify the desired clock by having
+the clock ID in its "clocks" phandle cell. The clock ID is directly mapped to
+the corresponding clock gating control bit in HW to ease manual clock lookup
+in datasheet.
+
+The following is a list of provided IDs for Armada 370:
+ID	Clock	Peripheral
+-----------------------------------
+0	Audio	AC97 Cntrl
+1	pex0_en	PCIe 0 Clock out
+2	pex1_en	PCIe 1 Clock out
+3	ge1	Gigabit Ethernet 1
+4	ge0	Gigabit Ethernet 0
+5	pex0	PCIe Cntrl 0
+9	pex1	PCIe Cntrl 1
+15	sata0	SATA Host 0
+17	sdio	SDHCI Host
+25	tdm	Time Division Mplx
+28	ddr	DDR Cntrl
+30	sata1	SATA Host 0
+
+The following is a list of provided IDs for Armada XP:
+ID	Clock	Peripheral
+-----------------------------------
+0	audio	Audio Cntrl
+1	ge3	Gigabit Ethernet 3
+2	ge2	Gigabit Ethernet 2
+3	ge1	Gigabit Ethernet 1
+4	ge0	Gigabit Ethernet 0
+5	pex0	PCIe Cntrl 0
+6	pex1	PCIe Cntrl 1
+7	pex2	PCIe Cntrl 2
+8	pex3	PCIe Cntrl 3
+13	bp
+14	sata0lnk
+15	sata0	SATA Host 0
+16	lcd	LCD Cntrl
+17	sdio	SDHCI Host
+18	usb0	USB Host 0
+19	usb1	USB Host 1
+20	usb2	USB Host 2
+22	xor0	XOR DMA 0
+23	crypto	CESA engine
+25	tdm	Time Division Mplx
+28	xor1	XOR DMA 1
+29	sata1lnk
+30	sata1	SATA Host 0
+
+The following is a list of provided IDs for Dove:
+ID	Clock	Peripheral
+-----------------------------------
+0	usb0	USB Host 0
+1	usb1	USB Host 1
+2	ge	Gigabit Ethernet
+3	sata	SATA Host
+4	pex0	PCIe Cntrl 0
+5	pex1	PCIe Cntrl 1
+8	sdio0	SDHCI Host 0
+9	sdio1	SDHCI Host 1
+10	nand	NAND Cntrl
+11	camera	Camera Cntrl
+12	i2s0	I2S Cntrl 0
+13	i2s1	I2S Cntrl 1
+15	crypto	CESA engine
+21	ac97	AC97 Cntrl
+22	pdma	Peripheral DMA
+23	xor0	XOR DMA 0
+24	xor1	XOR DMA 1
+30	gephy	Gigabit Ethernel PHY
+Note: gephy(30) is implemented as a parent clock of ge(2)
+
+The following is a list of provided IDs for Kirkwood:
+ID	Clock	Peripheral
+-----------------------------------
+0	ge0	Gigabit Ethernet 0
+2	pex0	PCIe Cntrl 0
+3	usb0	USB Host 0
+4	sdio	SDIO Cntrl
+5	tsu	Transp. Stream Unit
+6	dunit	SDRAM Cntrl
+7	runit	Runit
+8	xor0	XOR DMA 0
+9	audio	I2S Cntrl 0
+14	sata0	SATA Host 0
+15	sata1	SATA Host 1
+16	xor1	XOR DMA 1
+17	crypto	CESA engine
+18	pex1	PCIe Cntrl 1
+19	ge1	Gigabit Ethernet 0
+20	tdm	Time Division Mplx
+
+Required properties:
+- compatible : shall be one of the following:
+	"marvell,dove-gating-clock" - for Dove SoC clock gating
+	"marvell,kirkwood-gating-clock" - for Kirkwood SoC clock gating
+- reg : shall be the register address of the Clock Gating Control register
+- #clock-cells : from common clock binding; shall be set to 1
+
+Optional properties:
+- clocks : default parent clock phandle (e.g. tclk)
+
+Example:
+
+gate_clk: clock-gating-control@d0038 {
+	compatible = "marvell,dove-gating-clock";
+	reg = <0xd0038 0x4>;
+	/* default parent clock is tclk */
+	clocks = <&core_clk 0>;
+	#clock-cells = <1>;
+};
+
+sdio0: sdio@92000 {
+	compatible = "marvell,dove-sdhci";
+	/* get clk gate bit 8 (sdio0) */
+	clocks = <&gate_clk 8>;
+};
diff --git a/Documentation/devicetree/bindings/dma/mv-xor.txt b/Documentation/devicetree/bindings/dma/mv-xor.txt
new file mode 100644
index 0000000..7c6cb7f
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/mv-xor.txt
@@ -0,0 +1,40 @@
+* Marvell XOR engines
+
+Required properties:
+- compatible: Should be "marvell,orion-xor"
+- reg: Should contain registers location and length (two sets)
+    the first set is the low registers, the second set the high
+    registers for the XOR engine.
+- clocks: pointer to the reference clock
+
+The DT node must also contains sub-nodes for each XOR channel that the
+XOR engine has. Those sub-nodes have the following required
+properties:
+- interrupts: interrupt of the XOR channel
+
+And the following optional properties:
+- dmacap,memcpy to indicate that the XOR channel is capable of memcpy operations
+- dmacap,memset to indicate that the XOR channel is capable of memset operations
+- dmacap,xor to indicate that the XOR channel is capable of xor operations
+
+Example:
+
+xor@d0060900 {
+	compatible = "marvell,orion-xor";
+	reg = <0xd0060900 0x100
+	       0xd0060b00 0x100>;
+	clocks = <&coreclk 0>;
+	status = "okay";
+
+	xor00 {
+	      interrupts = <51>;
+	      dmacap,memcpy;
+	      dmacap,xor;
+	};
+	xor01 {
+	      interrupts = <52>;
+	      dmacap,memcpy;
+	      dmacap,xor;
+	      dmacap,memset;
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
new file mode 100644
index 0000000..859a6fa
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -0,0 +1,23 @@
+* Marvell Armada 370 / Armada XP Ethernet Controller (NETA)
+
+Required properties:
+- compatible: should be "marvell,armada-370-neta".
+- reg: address and length of the register set for the device.
+- interrupts: interrupt for the device
+- phy: A phandle to a phy node defining the PHY address (as the reg
+  property, a single integer).
+- phy-mode: The interface between the SoC and the PHY (a string that
+  of_get_phy_mode() can understand)
+- clocks: a pointer to the reference clock for this device.
+
+Example:
+
+ethernet@d0070000 {
+	compatible = "marvell,armada-370-neta";
+	reg = <0xd0070000 0x2500>;
+	interrupts = <8>;
+	clocks = <&gate_clk 4>;
+	status = "okay";
+	phy = <&phy0>;
+	phy-mode = "rgmii-id";
+};
diff --git a/Documentation/devicetree/bindings/net/marvell-orion-mdio.txt b/Documentation/devicetree/bindings/net/marvell-orion-mdio.txt
new file mode 100644
index 0000000..34e7aaf
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/marvell-orion-mdio.txt
@@ -0,0 +1,35 @@
+* Marvell MDIO Ethernet Controller interface
+
+The Ethernet controllers of the Marvel Kirkwood, Dove, Orion5x,
+MV78xx0, Armada 370 and Armada XP have an identical unit that provides
+an interface with the MDIO bus. This driver handles this MDIO
+interface.
+
+Required properties:
+- compatible: "marvell,orion-mdio"
+- reg: address and length of the SMI register
+
+The child nodes of the MDIO driver are the individual PHY devices
+connected to this MDIO bus. They must have a "reg" property given the
+PHY address on the MDIO bus.
+
+Example at the SoC level:
+
+mdio {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "marvell,orion-mdio";
+	reg = <0xd0072004 0x4>;
+};
+
+And at the board level:
+
+mdio {
+	phy0: ethernet-phy@0 {
+		reg = <0>;
+	};
+
+	phy1: ethernet-phy@1 {
+		reg = <1>;
+	};
+}
diff --git a/MAINTAINERS b/MAINTAINERS
index ff24a96..b95ae9b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4871,6 +4871,12 @@ S:	Maintained
 F:	drivers/net/ethernet/marvell/mv643xx_eth.*
 F:	include/linux/mv643xx.h
 
+MARVELL MVNETA ETHERNET DRIVER
+M:	Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/marvell/mvneta.*
+
 MARVELL MWIFIEX WIRELESS DRIVER
 M:	Bing Zhao <bzhao@marvell.com>
 L:	linux-wireless@vger.kernel.org
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2277f95..8c83d98 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -533,6 +533,7 @@ config ARCH_IXP4XX
 config ARCH_DOVE
 	bool "Marvell Dove"
 	select ARCH_REQUIRE_GPIOLIB
+	select COMMON_CLK_DOVE
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select MIGHT_HAVE_PCI
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index d0ae1d3..0f44174 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -77,7 +77,9 @@ dtb-$(CONFIG_ARCH_KIRKWOOD) += kirkwood-dns320.dtb \
 dtb-$(CONFIG_ARCH_MSM) += msm8660-surf.dtb \
 	msm8960-cdp.dtb
 dtb-$(CONFIG_ARCH_MVEBU) += armada-370-db.dtb \
-	armada-xp-db.dtb
+	armada-370-mirabox.dtb \
+	armada-xp-db.dtb \
+	armada-xp-openblocks-ax3-4.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx51-babbage.dtb \
 	imx53-ard.dtb \
 	imx53-evk.dtb \
diff --git a/arch/arm/boot/dts/armada-370-db.dts b/arch/arm/boot/dts/armada-370-db.dts
index fffd5c2..0004402 100644
--- a/arch/arm/boot/dts/armada-370-db.dts
+++ b/arch/arm/boot/dts/armada-370-db.dts
@@ -34,9 +34,30 @@
 			clock-frequency = <200000000>;
 			status = "okay";
 		};
-		timer@d0020300 {
-			clock-frequency = <600000000>;
+		sata@d00a0000 {
+			nr-ports = <2>;
 			status = "okay";
 		};
+
+		mdio {
+			phy0: ethernet-phy@0 {
+				reg = <0>;
+			};
+
+			phy1: ethernet-phy@1 {
+				reg = <1>;
+			};
+		};
+
+		ethernet@d0070000 {
+			status = "okay";
+			phy = <&phy0>;
+			phy-mode = "rgmii-id";
+		};
+		ethernet@d0074000 {
+			status = "okay";
+			phy = <&phy1>;
+			phy-mode = "rgmii-id";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-370-mirabox.dts b/arch/arm/boot/dts/armada-370-mirabox.dts
new file mode 100644
index 0000000..3b40713
--- /dev/null
+++ b/arch/arm/boot/dts/armada-370-mirabox.dts
@@ -0,0 +1,56 @@
+/*
+ * Device Tree file for Globalscale Mirabox
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+/dts-v1/;
+/include/ "armada-370.dtsi"
+
+/ {
+	model = "Globalscale Mirabox";
+	compatible = "globalscale,mirabox", "marvell,armada370", "marvell,armada-370-xp";
+
+	chosen {
+		bootargs = "console=ttyS0,115200 earlyprintk";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x20000000>; /* 512 MB */
+	};
+
+	soc {
+		serial@d0012000 {
+			clock-frequency = <200000000>;
+			status = "okay";
+		};
+		timer@d0020300 {
+			clock-frequency = <600000000>;
+			status = "okay";
+		};
+		mdio {
+			phy0: ethernet-phy@0 {
+				reg = <0>;
+			};
+
+			phy1: ethernet-phy@1 {
+				reg = <1>;
+			};
+		};
+		ethernet@d0070000 {
+			status = "okay";
+			phy = <&phy0>;
+			phy-mode = "rgmii-id";
+		};
+		ethernet@d0074000 {
+			status = "okay";
+			phy = <&phy1>;
+			phy-mode = "rgmii-id";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 16cc82c..cf6c48a 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -20,7 +20,7 @@
 
 / {
 	model = "Marvell Armada 370 and XP SoC";
-	compatible = "marvell,armada_370_xp";
+	compatible = "marvell,armada-370-xp";
 
 	cpus {
 		cpu@0 {
@@ -36,6 +36,12 @@
 	      interrupt-controller;
 	};
 
+	coherency-fabric@d0020200 {
+		compatible = "marvell,coherency-fabric";
+		reg = <0xd0020200 0xb0>,
+		      <0xd0021810 0x1c>;
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -62,12 +68,67 @@
 			       compatible = "marvell,armada-370-xp-timer";
 			       reg = <0xd0020300 0x30>;
 			       interrupts = <37>, <38>, <39>, <40>;
+			       clocks = <&coreclk 2>;
 		};
 
 		addr-decoding@d0020000 {
 			compatible = "marvell,armada-addr-decoding-controller";
 			reg = <0xd0020000 0x258>;
 		};
+
+		sata@d00a0000 {
+			compatible = "marvell,orion-sata";
+			reg = <0xd00a0000 0x2400>;
+			interrupts = <55>;
+			clocks = <&gateclk 15>, <&gateclk 30>;
+			clock-names = "0", "1";
+			status = "disabled";
+		};
+
+		mdio {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "marvell,orion-mdio";
+			reg = <0xd0072004 0x4>;
+		};
+
+		ethernet@d0070000 {
+				compatible = "marvell,armada-370-neta";
+				reg = <0xd0070000 0x2500>;
+				interrupts = <8>;
+				clocks = <&gateclk 4>;
+				status = "disabled";
+		};
+
+		ethernet@d0074000 {
+				compatible = "marvell,armada-370-neta";
+				reg = <0xd0074000 0x2500>;
+				interrupts = <10>;
+				clocks = <&gateclk 3>;
+				status = "disabled";
+		};
+
+		i2c0: i2c@d0011000 {
+			compatible = "marvell,mv64xxx-i2c";
+			reg = <0xd0011000 0x20>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <31>;
+			timeout-ms = <1000>;
+			clocks = <&coreclk 0>;
+			status = "disabled";
+		};
+
+		i2c1: i2c@d0011100 {
+			compatible = "marvell,mv64xxx-i2c";
+			reg = <0xd0011100 0x20>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <32>;
+			timeout-ms = <1000>;
+			clocks = <&coreclk 0>;
+			status = "disabled";
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 2069151..636cf7d 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -20,6 +20,12 @@
 / {
 	model = "Marvell Armada 370 family SoC";
 	compatible = "marvell,armada370", "marvell,armada-370-xp";
+	L2: l2-cache {
+		compatible = "marvell,aurora-outer-cache";
+		reg = <0xd0008000 0x1000>;
+		cache-id-part = <0x100>;
+		wt-override;
+	};
 
 	aliases {
 		gpio0 = &gpio0;
@@ -75,5 +81,56 @@
 			#interrupts-cells = <2>;
 			interrupts = <91>;
 		};
+
+		coreclk: mvebu-sar@d0018230 {
+			compatible = "marvell,armada-370-core-clock";
+			reg = <0xd0018230 0x08>;
+			#clock-cells = <1>;
+		};
+
+		gateclk: clock-gating-control@d0018220 {
+			compatible = "marvell,armada-370-gating-clock";
+			reg = <0xd0018220 0x4>;
+			clocks = <&coreclk 0>;
+			#clock-cells = <1>;
+		};
+
+		xor@d0060800 {
+			compatible = "marvell,orion-xor";
+			reg = <0xd0060800 0x100
+			       0xd0060A00 0x100>;
+			status = "okay";
+
+			xor00 {
+				interrupts = <51>;
+				dmacap,memcpy;
+				dmacap,xor;
+			};
+			xor01 {
+				interrupts = <52>;
+				dmacap,memcpy;
+				dmacap,xor;
+				dmacap,memset;
+			};
+		};
+
+		xor@d0060900 {
+			compatible = "marvell,orion-xor";
+			reg = <0xd0060900 0x100
+			       0xd0060b00 0x100>;
+			status = "okay";
+
+			xor10 {
+				interrupts = <94>;
+				dmacap,memcpy;
+				dmacap,xor;
+			};
+			xor11 {
+				interrupts = <95>;
+				dmacap,memcpy;
+				dmacap,xor;
+				dmacap,memset;
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts
index b1fc728..8e53b25 100644
--- a/arch/arm/boot/dts/armada-xp-db.dts
+++ b/arch/arm/boot/dts/armada-xp-db.dts
@@ -46,5 +46,49 @@
 			clock-frequency = <250000000>;
 			status = "okay";
 		};
+
+		sata@d00a0000 {
+			nr-ports = <2>;
+			status = "okay";
+		};
+
+		mdio {
+			phy0: ethernet-phy@0 {
+				reg = <0>;
+			};
+
+			phy1: ethernet-phy@1 {
+				reg = <1>;
+			};
+
+			phy2: ethernet-phy@2 {
+				reg = <25>;
+			};
+
+			phy3: ethernet-phy@3 {
+				reg = <27>;
+			};
+		};
+
+		ethernet@d0070000 {
+			status = "okay";
+			phy = <&phy0>;
+			phy-mode = "rgmii-id";
+		};
+		ethernet@d0074000 {
+			status = "okay";
+			phy = <&phy1>;
+			phy-mode = "rgmii-id";
+		};
+		ethernet@d0030000 {
+			status = "okay";
+			phy = <&phy2>;
+			phy-mode = "sgmii";
+		};
+		ethernet@d0034000 {
+			status = "okay";
+			phy = <&phy3>;
+			phy-mode = "sgmii";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
index ea35519..c45c7b4 100644
--- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
@@ -24,6 +24,18 @@
 		gpio1 = &gpio1;
 	};
 
+	cpus {
+	    #address-cells = <1>;
+	    #size-cells = <0>;
+
+	    cpu@0 {
+		device_type = "cpu";
+		compatible = "marvell,sheeva-v7";
+		reg = <0>;
+		clocks = <&cpuclk 0>;
+	    };
+	}
+
 	soc {
 		pinctrl {
 			compatible = "marvell,mv78230-pinctrl";
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 2057863..a2aee57 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -25,6 +25,25 @@
 		gpio2 = &gpio2;
 	};
 
+	cpus {
+	    #address-cells = <1>;
+	    #size-cells = <0>;
+
+	    cpu@0 {
+		device_type = "cpu";
+		compatible = "marvell,sheeva-v7";
+		reg = <0>;
+		clocks = <&cpuclk 0>;
+	    };
+
+	    cpu@1 {
+		device_type = "cpu";
+		compatible = "marvell,sheeva-v7";
+		reg = <1>;
+		clocks = <&cpuclk 1>;
+	    };
+	};
+
 	soc {
 		pinctrl {
 			compatible = "marvell,mv78260-pinctrl";
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index ffac983..da03a12 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -25,6 +25,40 @@
 		gpio2 = &gpio2;
 	};
 
+
+	cpus {
+	    #address-cells = <1>;
+	    #size-cells = <0>;
+
+	    cpu@0 {
+		device_type = "cpu";
+		compatible = "marvell,sheeva-v7";
+		reg = <0>;
+		clocks = <&cpuclk 0>;
+	    };
+
+	    cpu@1 {
+		device_type = "cpu";
+		compatible = "marvell,sheeva-v7";
+		reg = <1>;
+		clocks = <&cpuclk 1>;
+	    };
+
+	    cpu@2 {
+		device_type = "cpu";
+		compatible = "marvell,sheeva-v7";
+		reg = <2>;
+		clocks = <&cpuclk 2>;
+	    };
+
+	    cpu@3 {
+		device_type = "cpu";
+		compatible = "marvell,sheeva-v7";
+		reg = <3>;
+		clocks = <&cpuclk 3>;
+	    };
+	};
+
 	soc {
 		pinctrl {
 			compatible = "marvell,mv78460-pinctrl";
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
new file mode 100644
index 0000000..b42652f
--- /dev/null
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -0,0 +1,125 @@
+/*
+ * Device Tree file for OpenBlocks AX3-4 board
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+/dts-v1/;
+/include/ "armada-xp-mv78260.dtsi"
+
+/ {
+	model = "PlatHome OpenBlocks AX3-4 board";
+	compatible = "plathome,openblocks-ax3-4", "marvell,armadaxp-mv78260", "marvell,armadaxp", "marvell,armada-370-xp";
+
+	chosen {
+		bootargs = "console=ttyS0,115200 earlyprintk";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0xC0000000>; /* 3 GB */
+	};
+
+	soc {
+		serial@d0012000 {
+			clock-frequency = <250000000>;
+			status = "okay";
+		};
+		serial@d0012100 {
+			clock-frequency = <250000000>;
+			status = "okay";
+		};
+		pinctrl {
+			led_pins: led-pins-0 {
+				marvell,pins = "mpp49", "mpp51", "mpp53";
+				marvell,function = "gpio";
+			};
+		};
+		leds {
+			compatible = "gpio-leds";
+			pinctrl-names = "default";
+			pinctrl-0 = <&led_pins>;
+
+			red_led {
+				label = "red_led";
+				gpios = <&gpio1 17 1>;
+				default-state = "off";
+			};
+
+			yellow_led {
+				label = "yellow_led";
+				gpios = <&gpio1 19 1>;
+				default-state = "off";
+			};
+
+			green_led {
+				label = "green_led";
+				gpios = <&gpio1 21 1>;
+				default-state = "off";
+				linux,default-trigger = "heartbeat";
+			};
+		};
+
+		mdio {
+			phy0: ethernet-phy@0 {
+				reg = <0>;
+			};
+
+			phy1: ethernet-phy@1 {
+				reg = <1>;
+			};
+
+			phy2: ethernet-phy@2 {
+				reg = <2>;
+			};
+
+			phy3: ethernet-phy@3 {
+				reg = <3>;
+			};
+		};
+
+		ethernet@d0070000 {
+			status = "okay";
+			phy = <&phy0>;
+			phy-mode = "sgmii";
+		};
+		ethernet@d0074000 {
+			status = "okay";
+			phy = <&phy1>;
+			phy-mode = "sgmii";
+		};
+		ethernet@d0030000 {
+			status = "okay";
+			phy = <&phy2>;
+			phy-mode = "sgmii";
+		};
+		ethernet@d0034000 {
+			status = "okay";
+			phy = <&phy3>;
+			phy-mode = "sgmii";
+		};
+		i2c@d0011000 {
+			status = "okay";
+			clock-frequency = <400000>;
+		};
+		i2c@d0011100 {
+			status = "okay";
+			clock-frequency = <400000>;
+
+			s35390a: s35390a@30 {
+				compatible = "s35390a";
+				reg = <0x30>;
+			};
+		};
+		sata@d00a0000 {
+			nr-ports = <2>;
+			status = "okay";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index 71d6b5d..367aa3f 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -22,9 +22,22 @@
 	model = "Marvell Armada XP family SoC";
 	compatible = "marvell,armadaxp", "marvell,armada-370-xp";
 
+	L2: l2-cache {
+		compatible = "marvell,aurora-system-cache";
+		reg = <0xd0008000 0x1000>;
+		cache-id-part = <0x100>;
+		wt-override;
+	};
+
 	mpic: interrupt-controller@d0020000 {
 	      reg = <0xd0020a00 0x1d0>,
-		    <0xd0021870 0x58>;
+		    <0xd0021070 0x58>;
+	};
+
+	armada-370-xp-pmsu@d0022000 {
+		compatible = "marvell,armada-370-xp-pmsu";
+		reg = <0xd0022100 0x430>,
+		      <0xd0020800 0x20>;
 	};
 
 	soc {
@@ -47,9 +60,85 @@
 				marvell,timer-25Mhz;
 		};
 
+		coreclk: mvebu-sar@d0018230 {
+			compatible = "marvell,armada-xp-core-clock";
+			reg = <0xd0018230 0x08>;
+			#clock-cells = <1>;
+		};
+
+		cpuclk: clock-complex@d0018700 {
+			#clock-cells = <1>;
+			compatible = "marvell,armada-xp-cpu-clock";
+			reg = <0xd0018700 0xA0>;
+			clocks = <&coreclk 1>;
+		};
+
+		gateclk: clock-gating-control@d0018220 {
+			compatible = "marvell,armada-xp-gating-clock";
+			reg = <0xd0018220 0x4>;
+			clocks = <&coreclk 0>;
+			#clock-cells = <1>;
+		};
+
 		system-controller@d0018200 {
 				compatible = "marvell,armada-370-xp-system-controller";
 				reg = <0xd0018200 0x500>;
 		};
+
+		ethernet@d0030000 {
+				compatible = "marvell,armada-370-neta";
+				reg = <0xd0030000 0x2500>;
+				interrupts = <12>;
+				clocks = <&gateclk 2>;
+				status = "disabled";
+		};
+
+		ethernet@d0034000 {
+				compatible = "marvell,armada-370-neta";
+				reg = <0xd0034000 0x2500>;
+				interrupts = <14>;
+				clocks = <&gateclk 1>;
+				status = "disabled";
+		};
+
+		xor@d0060900 {
+			compatible = "marvell,orion-xor";
+			reg = <0xd0060900 0x100
+			       0xd0060b00 0x100>;
+			clocks = <&gateclk 22>;
+			status = "okay";
+
+			xor10 {
+				interrupts = <51>;
+				dmacap,memcpy;
+				dmacap,xor;
+			};
+			xor11 {
+				interrupts = <52>;
+				dmacap,memcpy;
+				dmacap,xor;
+				dmacap,memset;
+			};
+		};
+
+		xor@d00f0900 {
+			compatible = "marvell,orion-xor";
+			reg = <0xd00F0900 0x100
+			       0xd00F0B00 0x100>;
+			clocks = <&gateclk 28>;
+			status = "okay";
+
+			xor00 {
+				interrupts = <94>;
+				dmacap,memcpy;
+				dmacap,xor;
+			};
+			xor01 {
+				interrupts = <95>;
+				dmacap,memcpy;
+				dmacap,xor;
+				dmacap,memset;
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi
index 61f3914..f3f7e9d 100644
--- a/arch/arm/boot/dts/dove.dtsi
+++ b/arch/arm/boot/dts/dove.dtsi
@@ -37,6 +37,19 @@
 			reg = <0x20204 0x04>, <0x20214 0x04>;
 		};
 
+		core_clk: core-clocks@d0214 {
+			compatible = "marvell,dove-core-clock";
+			reg = <0xd0214 0x4>;
+			#clock-cells = <1>;
+		};
+
+		gate_clk: clock-gating-control@d0038 {
+			compatible = "marvell,dove-gating-clock";
+			reg = <0xd0038 0x4>;
+			clocks = <&core_clk 0>;
+			#clock-cells = <1>;
+		};
+
 		uart0: serial@12000 {
 			compatible = "ns16550a";
 			reg = <0x12000 0x100>;
@@ -113,6 +126,7 @@
 			cell-index = <0>;
 			interrupts = <6>;
 			reg = <0x10600 0x28>;
+			clocks = <&core_clk 0>;
 			status = "disabled";
 		};
 
@@ -123,6 +137,7 @@
 			cell-index = <1>;
 			interrupts = <5>;
 			reg = <0x14600 0x28>;
+			clocks = <&core_clk 0>;
 			status = "disabled";
 		};
 
@@ -134,6 +149,7 @@
 			interrupts = <11>;
 			clock-frequency = <400000>;
 			timeout-ms = <1000>;
+			clocks = <&core_clk 0>;
 			status = "disabled";
 		};
 
@@ -141,6 +157,7 @@
 			compatible = "marvell,dove-sdhci";
 			reg = <0x92000 0x100>;
 			interrupts = <35>, <37>;
+			clocks = <&gate_clk 8>;
 			status = "disabled";
 		};
 
@@ -148,6 +165,7 @@
 			compatible = "marvell,dove-sdhci";
 			reg = <0x90000 0x100>;
 			interrupts = <36>, <38>;
+			clocks = <&gate_clk 9>;
 			status = "disabled";
 		};
 
@@ -155,6 +173,7 @@
 			compatible = "marvell,orion-sata";
 			reg = <0xa0000 0x2400>;
 			interrupts = <62>;
+			clocks = <&gate_clk 3>;
 			nr-ports = <1>;
 			status = "disabled";
 		};
@@ -165,7 +184,50 @@
 			      <0xc8000000 0x800>;
 			reg-names = "regs", "sram";
 			interrupts = <31>;
+			clocks = <&gate_clk 15>;
+			status = "okay";
+		};
+
+		xor0: dma-engine@60800 {
+			compatible = "marvell,orion-xor";
+			reg = <0x60800 0x100
+			       0x60a00 0x100>;
+			clocks = <&gate_clk 23>;
 			status = "okay";
+
+			channel0 {
+				interrupts = <39>;
+				dmacap,memcpy;
+				dmacap,xor;
+			};
+
+			channel1 {
+				interrupts = <40>;
+				dmacap,memset;
+				dmacap,memcpy;
+				dmacap,xor;
+			};
+		};
+
+		xor1: dma-engine@60900 {
+			compatible = "marvell,orion-xor";
+			reg = <0x60900 0x100
+			       0x60b00 0x100>;
+			clocks = <&gate_clk 24>;
+			status = "okay";
+
+			channel0 {
+				interrupts = <42>;
+				dmacap,memcpy;
+				dmacap,xor;
+			};
+
+			channel1 {
+				interrupts = <43>;
+				dmacap,memset;
+				dmacap,memcpy;
+				dmacap,xor;
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/kirkwood.dtsi b/arch/arm/boot/dts/kirkwood.dtsi
index a990c30..7735cee 100644
--- a/arch/arm/boot/dts/kirkwood.dtsi
+++ b/arch/arm/boot/dts/kirkwood.dtsi
@@ -23,6 +23,12 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 
+		core_clk: core-clocks@10030 {
+			compatible = "marvell,kirkwood-core-clock";
+			reg = <0x10030 0x4>;
+	        	#clock-cells = <1>;
+		};
+
 		gpio0: gpio@10100 {
 			compatible = "marvell,orion-gpio";
 			#gpio-cells = <2>;
@@ -48,6 +54,7 @@
 			reg = <0x12000 0x100>;
 			reg-shift = <2>;
 			interrupts = <33>;
+			clocks = <&gate_clk 7>;
 			/* set clock-frequency in board dts */
 			status = "disabled";
 		};
@@ -57,6 +64,7 @@
 			reg = <0x12100 0x100>;
 			reg-shift = <2>;
 			interrupts = <34>;
+			clocks = <&gate_clk 7>;
 			/* set clock-frequency in board dts */
 			status = "disabled";
 		};
@@ -74,13 +82,62 @@
 			cell-index = <0>;
 			interrupts = <23>;
 			reg = <0x10600 0x28>;
+			clocks = <&gate_clk 7>;
 			status = "disabled";
 		};
 
+		gate_clk: clock-gating-control@2011c {
+			compatible = "marvell,kirkwood-gating-clock";
+			reg = <0x2011c 0x4>;
+			clocks = <&core_clk 0>;
+			#clock-cells = <1>;
+		};
+
 		wdt@20300 {
 			compatible = "marvell,orion-wdt";
 			reg = <0x20300 0x28>;
+			clocks = <&gate_clk 7>;
+			status = "okay";
+		};
+
+		xor@60800 {
+			compatible = "marvell,orion-xor";
+			reg = <0x60800 0x100
+			       0x60A00 0x100>;
+			status = "okay";
+			clocks = <&gate_clk 8>;
+
+			xor00 {
+			      interrupts = <5>;
+			      dmacap,memcpy;
+			      dmacap,xor;
+			};
+			xor01 {
+			      interrupts = <6>;
+			      dmacap,memcpy;
+			      dmacap,xor;
+			      dmacap,memset;
+			};
+		};
+
+		xor@60900 {
+			compatible = "marvell,orion-xor";
+			reg = <0x60900 0x100
+			       0xd0B00 0x100>;
 			status = "okay";
+			clocks = <&gate_clk 16>;
+
+			xor00 {
+			      interrupts = <7>;
+			      dmacap,memcpy;
+			      dmacap,xor;
+			};
+			xor01 {
+			      interrupts = <8>;
+			      dmacap,memcpy;
+			      dmacap,xor;
+			      dmacap,memset;
+			};
 		};
 
 		ehci@50000 {
@@ -94,6 +151,8 @@
 			compatible = "marvell,orion-sata";
 			reg = <0x80000 0x5000>;
 			interrupts = <21>;
+			clocks = <&gate_clk 14>, <&gate_clk 15>;
+			clock-names = "0", "1";
 			status = "disabled";
 		};
 
@@ -107,6 +166,7 @@
 			reg = <0x3000000 0x400>;
 			chip-delay = <25>;
 			/* set partition map and/or chip-delay in board dts */
+			clocks = <&gate_clk 7>;
 			status = "disabled";
 		};
 
@@ -117,6 +177,7 @@
 			#size-cells = <0>;
 			interrupts = <29>;
 			clock-frequency = <100000>;
+			clocks = <&gate_clk 7>;
 			status = "disabled";
 		};
 
@@ -126,6 +187,7 @@
 			      <0xf5000000 0x800>;
 			reg-names = "regs", "sram";
 			interrupts = <22>;
+			clocks = <&gate_clk 17>;
 			status = "okay";
 		};
 	};
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 159f75f..dbea6f4 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -17,8 +17,10 @@ CONFIG_ARM_APPENDED_DTB=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_NET=y
+CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_SATA_HIGHBANK=y
+CONFIG_SATA_MV=y
 CONFIG_NETDEVICES=y
 CONFIG_NET_CALXEDA_XGMAC=y
 CONFIG_SMSC911X=y
diff --git a/arch/arm/configs/mvebu_defconfig b/arch/arm/configs/mvebu_defconfig
index 3458752..a702fb3 100644
--- a/arch/arm/configs/mvebu_defconfig
+++ b/arch/arm/configs/mvebu_defconfig
@@ -12,6 +12,9 @@ CONFIG_ARCH_MVEBU=y
 CONFIG_MACH_ARMADA_370=y
 CONFIG_MACH_ARMADA_XP=y
 # CONFIG_CACHE_L2X0 is not set
+# CONFIG_SWP_EMULATE is not set
+CONFIG_SMP=y
+# CONFIG_LOCAL_TIMERS is not set
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 # CONFIG_COMPACTION is not set
@@ -19,13 +22,27 @@ CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_VFP=y
+CONFIG_NET=y
+CONFIG_INET=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_BLK_DEV_SD=y
+CONFIG_ATA=y
+CONFIG_SATA_MV=y
+CONFIG_NETDEVICES=y
+CONFIG_MVNETA=y
+CONFIG_MARVELL_PHY=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_I2C=y
+CONFIG_I2C_MV64XXX=y
 CONFIG_GPIOLIB=y
 CONFIG_GPIO_SYSFS=y
 # CONFIG_USB_SUPPORT is not set
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_S35390A=y
+CONFIG_DMADEVICES=y
+CONFIG_MV_XOR=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 8ea02ac..67d0632 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -111,6 +111,8 @@ static inline void dma_free_noncoherent(struct device *dev, size_t size,
 
 extern int dma_supported(struct device *dev, u64 mask);
 
+extern int arm_dma_set_mask(struct device *dev, u64 dma_mask);
+
 /**
  * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/arch/arm/mach-dove/Kconfig b/arch/arm/mach-dove/Kconfig
index 00154e7..603c5fd 100644
--- a/arch/arm/mach-dove/Kconfig
+++ b/arch/arm/mach-dove/Kconfig
@@ -17,6 +17,8 @@ config MACH_CM_A510
 
 config MACH_DOVE_DT
 	bool "Marvell Dove Flattened Device Tree"
+	select MVEBU_CLK_CORE
+	select MVEBU_CLK_GATING
 	select USE_OF
 	help
 	  Say 'Y' here if you want your kernel to support the
diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c
index f723fe1..89f4f99 100644
--- a/arch/arm/mach-dove/common.c
+++ b/arch/arm/mach-dove/common.c
@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/pci.h>
 #include <linux/clk-provider.h>
+#include <linux/clk/mvebu.h>
 #include <linux/ata_platform.h>
 #include <linux/gpio.h>
 #include <linux/of.h>
@@ -32,6 +33,7 @@
 #include <linux/irq.h>
 #include <plat/time.h>
 #include <linux/platform_data/usb-ehci-orion.h>
+#include <linux/platform_data/dma-mv_xor.h>
 #include <plat/irq.h>
 #include <plat/common.h>
 #include <plat/addr-map.h>
@@ -123,8 +125,8 @@ static void __init dove_clk_init(void)
 	orion_clkdev_add(NULL, "mv_crypto", crypto);
 	orion_clkdev_add(NULL, "dove-ac97", ac97);
 	orion_clkdev_add(NULL, "dove-pdma", pdma);
-	orion_clkdev_add(NULL, "mv_xor_shared.0", xor0);
-	orion_clkdev_add(NULL, "mv_xor_shared.1", xor1);
+	orion_clkdev_add(NULL, MV_XOR_NAME ".0", xor0);
+	orion_clkdev_add(NULL, MV_XOR_NAME ".1", xor1);
 }
 
 /*****************************************************************************
@@ -376,19 +378,44 @@ void dove_restart(char mode, const char *cmd)
 
 #if defined(CONFIG_MACH_DOVE_DT)
 /*
- * Auxdata required until real OF clock provider
+ * There are still devices that doesn't even know about DT,
+ * get clock gates here and add a clock lookup.
  */
-struct of_dev_auxdata dove_auxdata_lookup[] __initdata = {
-	OF_DEV_AUXDATA("marvell,orion-spi", 0xf1010600, "orion_spi.0", NULL),
-	OF_DEV_AUXDATA("marvell,orion-spi", 0xf1014600, "orion_spi.1", NULL),
-	OF_DEV_AUXDATA("marvell,orion-wdt", 0xf1020300, "orion_wdt", NULL),
-	OF_DEV_AUXDATA("marvell,mv64xxx-i2c", 0xf1011000, "mv64xxx_i2c.0",
-		       NULL),
-	OF_DEV_AUXDATA("marvell,orion-sata", 0xf10a0000, "sata_mv.0", NULL),
-	OF_DEV_AUXDATA("marvell,dove-sdhci", 0xf1092000, "sdhci-dove.0", NULL),
-	OF_DEV_AUXDATA("marvell,dove-sdhci", 0xf1090000, "sdhci-dove.1", NULL),
-	{},
-};
+static void __init dove_legacy_clk_init(void)
+{
+	struct device_node *np = of_find_compatible_node(NULL, NULL,
+					 "marvell,dove-gating-clock");
+	struct of_phandle_args clkspec;
+
+	clkspec.np = np;
+	clkspec.args_count = 1;
+
+	clkspec.args[0] = CLOCK_GATING_BIT_USB0;
+	orion_clkdev_add(NULL, "orion-ehci.0",
+			 of_clk_get_from_provider(&clkspec));
+
+	clkspec.args[0] = CLOCK_GATING_BIT_USB1;
+	orion_clkdev_add(NULL, "orion-ehci.1",
+			 of_clk_get_from_provider(&clkspec));
+
+	clkspec.args[0] = CLOCK_GATING_BIT_GBE;
+	orion_clkdev_add(NULL, "mv643xx_eth_port.0",
+			 of_clk_get_from_provider(&clkspec));
+
+	clkspec.args[0] = CLOCK_GATING_BIT_PCIE0;
+	orion_clkdev_add("0", "pcie",
+			 of_clk_get_from_provider(&clkspec));
+
+	clkspec.args[0] = CLOCK_GATING_BIT_PCIE1;
+	orion_clkdev_add("1", "pcie",
+			 of_clk_get_from_provider(&clkspec));
+}
+
+static void __init dove_of_clk_init(void)
+{
+	mvebu_clocks_init();
+	dove_legacy_clk_init();
+}
 
 static struct mv643xx_eth_platform_data dove_dt_ge00_data = {
 	.phy_addr = MV643XX_ETH_PHY_ADDR_DEFAULT,
@@ -405,20 +432,17 @@ static void __init dove_dt_init(void)
 	dove_setup_cpu_mbus();
 
 	/* Setup root of clk tree */
-	dove_clk_init();
+	dove_of_clk_init();
 
 	/* Internal devices not ported to DT yet */
 	dove_rtc_init();
-	dove_xor0_init();
-	dove_xor1_init();
 
 	dove_ge00_init(&dove_dt_ge00_data);
 	dove_ehci0_init();
 	dove_ehci1_init();
 	dove_pcie_init(1, 1);
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     dove_auxdata_lookup, NULL);
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char * const dove_dt_board_compat[] = {
diff --git a/arch/arm/mach-kirkwood/Kconfig b/arch/arm/mach-kirkwood/Kconfig
index 503d7dd..f91cdff 100644
--- a/arch/arm/mach-kirkwood/Kconfig
+++ b/arch/arm/mach-kirkwood/Kconfig
@@ -51,6 +51,8 @@ config ARCH_KIRKWOOD_DT
 	select POWER_RESET_GPIO
 	select REGULATOR
 	select REGULATOR_FIXED_VOLTAGE
+	select MVEBU_CLK_CORE
+	select MVEBU_CLK_GATING
 	select USE_OF
 	help
 	  Say 'Y' here if you want your kernel to support the
diff --git a/arch/arm/mach-kirkwood/board-dt.c b/arch/arm/mach-kirkwood/board-dt.c
index 375f7d88..ff4150a 100644
--- a/arch/arm/mach-kirkwood/board-dt.c
+++ b/arch/arm/mach-kirkwood/board-dt.c
@@ -14,11 +14,15 @@
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/clk-provider.h>
+#include <linux/clk/mvebu.h>
 #include <linux/kexec.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <mach/bridge-regs.h>
+#include <linux/platform_data/usb-ehci-orion.h>
 #include <plat/irq.h>
+#include <plat/common.h>
 #include "common.h"
 
 static struct of_device_id kirkwood_dt_match_table[] __initdata = {
@@ -26,18 +30,50 @@ static struct of_device_id kirkwood_dt_match_table[] __initdata = {
 	{ }
 };
 
-static struct of_dev_auxdata kirkwood_auxdata_lookup[] __initdata = {
-	OF_DEV_AUXDATA("marvell,orion-spi", 0xf1010600, "orion_spi.0", NULL),
-	OF_DEV_AUXDATA("marvell,mv64xxx-i2c", 0xf1011000, "mv64xxx_i2c.0",
-		       NULL),
-	OF_DEV_AUXDATA("marvell,mv64xxx-i2c", 0xf1011100, "mv64xxx_i2c.1",
-		       NULL),
-	OF_DEV_AUXDATA("marvell,orion-wdt", 0xf1020300, "orion_wdt", NULL),
-	OF_DEV_AUXDATA("marvell,orion-sata", 0xf1080000, "sata_mv.0", NULL),
-	OF_DEV_AUXDATA("marvell,orion-nand", 0xf4000000, "orion_nand", NULL),
-	OF_DEV_AUXDATA("marvell,orion-crypto", 0xf1030000, "mv_crypto", NULL),
-	{},
-};
+/*
+ * There are still devices that doesn't know about DT yet.  Get clock
+ * gates here and add a clock lookup alias, so that old platform
+ * devices still work.
+*/
+
+static void __init kirkwood_legacy_clk_init(void)
+{
+
+	struct device_node *np = of_find_compatible_node(
+		NULL, NULL, "marvell,kirkwood-gating-clock");
+
+	struct of_phandle_args clkspec;
+
+	clkspec.np = np;
+	clkspec.args_count = 1;
+
+	clkspec.args[0] = CGC_BIT_GE0;
+	orion_clkdev_add(NULL, "mv643xx_eth_port.0",
+			 of_clk_get_from_provider(&clkspec));
+
+	clkspec.args[0] = CGC_BIT_PEX0;
+	orion_clkdev_add("0", "pcie",
+			 of_clk_get_from_provider(&clkspec));
+
+	clkspec.args[0] = CGC_BIT_USB0;
+	orion_clkdev_add(NULL, "orion-ehci.0",
+			 of_clk_get_from_provider(&clkspec));
+
+	clkspec.args[0] = CGC_BIT_PEX1;
+	orion_clkdev_add("1", "pcie",
+			 of_clk_get_from_provider(&clkspec));
+
+	clkspec.args[0] = CGC_BIT_GE1;
+	orion_clkdev_add(NULL, "mv643xx_eth_port.1",
+			 of_clk_get_from_provider(&clkspec));
+
+}
+
+static void __init kirkwood_of_clk_init(void)
+{
+	mvebu_clocks_init();
+	kirkwood_legacy_clk_init();
+}
 
 static void __init kirkwood_dt_init(void)
 {
@@ -56,11 +92,7 @@ static void __init kirkwood_dt_init(void)
 	kirkwood_l2_init();
 
 	/* Setup root of clk tree */
-	kirkwood_clk_init();
-
-	/* internal devices that every board has */
-	kirkwood_xor0_init();
-	kirkwood_xor1_init();
+	kirkwood_of_clk_init();
 
 #ifdef CONFIG_KEXEC
 	kexec_reinit = kirkwood_enable_pcie;
@@ -115,8 +147,7 @@ static void __init kirkwood_dt_init(void)
 	if (of_machine_is_compatible("zyxel,nsa310"))
 		nsa310_init();
 
-	of_platform_populate(NULL, kirkwood_dt_match_table,
-			     kirkwood_auxdata_lookup, NULL);
+	of_platform_populate(NULL, kirkwood_dt_match_table, NULL, NULL);
 }
 
 static const char * const kirkwood_dt_board_compat[] = {
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index 5303be6..bac21a5 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -260,8 +260,8 @@ void __init kirkwood_clk_init(void)
 	orion_clkdev_add(NULL, "orion_nand", runit);
 	orion_clkdev_add(NULL, "mvsdio", sdio);
 	orion_clkdev_add(NULL, "mv_crypto", crypto);
-	orion_clkdev_add(NULL, MV_XOR_SHARED_NAME ".0", xor0);
-	orion_clkdev_add(NULL, MV_XOR_SHARED_NAME ".1", xor1);
+	orion_clkdev_add(NULL, MV_XOR_NAME ".0", xor0);
+	orion_clkdev_add(NULL, MV_XOR_NAME ".1", xor1);
 	orion_clkdev_add("0", "pcie", pex0);
 	orion_clkdev_add("1", "pcie", pex1);
 	orion_clkdev_add(NULL, "kirkwood-i2s", audio);
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 416d46e..440b13e 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -9,6 +9,10 @@ config ARCH_MVEBU
 	select PINCTRL
 	select PLAT_ORION
 	select SPARSE_IRQ
+	select CLKDEV_LOOKUP
+	select MVEBU_CLK_CORE
+	select MVEBU_CLK_CPU
+	select MVEBU_CLK_GATING
 
 if ARCH_MVEBU
 
@@ -17,7 +21,9 @@ menu "Marvell SOC with device tree"
 config MACH_ARMADA_370_XP
 	bool
 	select ARMADA_370_XP_TIMER
-	select CPU_V7
+	select HAVE_SMP
+	select CACHE_L2X0
+	select CPU_PJ4B
 
 config MACH_ARMADA_370
 	bool "Marvell Armada 370 boards"
diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile
index 57f996b..5dcb369 100644
--- a/arch/arm/mach-mvebu/Makefile
+++ b/arch/arm/mach-mvebu/Makefile
@@ -2,4 +2,6 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
 	-I$(srctree)/arch/arm/plat-orion/include
 
 obj-y += system-controller.o
-obj-$(CONFIG_MACH_ARMADA_370_XP) += armada-370-xp.o irq-armada-370-xp.o addr-map.o
+obj-$(CONFIG_MACH_ARMADA_370_XP) += armada-370-xp.o irq-armada-370-xp.o addr-map.o coherency.o coherency_ll.o pmsu.o
+obj-$(CONFIG_SMP)                += platsmp.o headsmp.o
+obj-$(CONFIG_HOTPLUG_CPU)        += hotplug.o
diff --git a/arch/arm/mach-mvebu/addr-map.c b/arch/arm/mach-mvebu/addr-map.c
index fe454a4..ab9b3bd 100644
--- a/arch/arm/mach-mvebu/addr-map.c
+++ b/arch/arm/mach-mvebu/addr-map.c
@@ -78,7 +78,7 @@ armada_cfg_base(const struct orion_addr_map_cfg *cfg, int win)
 	if (win < 8)
 		offset = (win << 4);
 	else
-		offset = ARMADA_WINDOW_8_PLUS_OFFSET + (win << 3);
+		offset = ARMADA_WINDOW_8_PLUS_OFFSET + ((win - 8) << 3);
 
 	return cfg->bridge_virt_base + offset;
 }
@@ -108,6 +108,9 @@ static int __init armada_setup_cpu_mbus(void)
 
 	addr_map_cfg.bridge_virt_base = mbus_unit_addr_decoding_base;
 
+	if (of_find_compatible_node(NULL, NULL, "marvell,coherency-fabric"))
+		addr_map_cfg.hw_io_coherency = 1;
+
 	/*
 	 * Disable, clear and configure windows.
 	 */
diff --git a/arch/arm/mach-mvebu/armada-370-xp.c b/arch/arm/mach-mvebu/armada-370-xp.c
index 49d7915..7434b5e 100644
--- a/arch/arm/mach-mvebu/armada-370-xp.c
+++ b/arch/arm/mach-mvebu/armada-370-xp.c
@@ -17,11 +17,14 @@
 #include <linux/of_platform.h>
 #include <linux/io.h>
 #include <linux/time-armada-370-xp.h>
+#include <linux/clk/mvebu.h>
+#include <linux/dma-mapping.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 #include "armada-370-xp.h"
 #include "common.h"
+#include "coherency.h"
 
 static struct map_desc armada_370_xp_io_desc[] __initdata = {
 	{
@@ -37,27 +40,45 @@ void __init armada_370_xp_map_io(void)
 	iotable_init(armada_370_xp_io_desc, ARRAY_SIZE(armada_370_xp_io_desc));
 }
 
+void __init armada_370_xp_timer_and_clk_init(void)
+{
+	mvebu_clocks_init();
+	armada_370_xp_timer_init();
+}
+
+void __init armada_370_xp_init_early(void)
+{
+	/*
+	 * Some Armada 370/XP devices allocate their coherent buffers
+	 * from atomic context. Increase size of atomic coherent pool
+	 * to make sure such the allocations won't fail.
+	 */
+	init_dma_coherent_pool_size(SZ_1M);
+}
+
 struct sys_timer armada_370_xp_timer = {
-	.init		= armada_370_xp_timer_init,
+	.init		= armada_370_xp_timer_and_clk_init,
 };
 
 static void __init armada_370_xp_dt_init(void)
 {
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+	coherency_init();
 }
 
-static const char * const armada_370_xp_dt_board_dt_compat[] = {
-	"marvell,a370-db",
-	"marvell,axp-db",
+static const char * const armada_370_xp_dt_compat[] = {
+	"marvell,armada-370-xp",
 	NULL,
 };
 
-DT_MACHINE_START(ARMADA_XP_DT, "Marvell Aramada 370/XP (Device Tree)")
+DT_MACHINE_START(ARMADA_XP_DT, "Marvell Armada 370/XP (Device Tree)")
+	.smp		= smp_ops(armada_xp_smp_ops),
 	.init_machine	= armada_370_xp_dt_init,
 	.map_io		= armada_370_xp_map_io,
+	.init_early	= armada_370_xp_init_early,
 	.init_irq	= armada_370_xp_init_irq,
 	.handle_irq     = armada_370_xp_handle_irq,
 	.timer		= &armada_370_xp_timer,
 	.restart	= mvebu_restart,
-	.dt_compat	= armada_370_xp_dt_board_dt_compat,
+	.dt_compat	= armada_370_xp_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-mvebu/armada-370-xp.h b/arch/arm/mach-mvebu/armada-370-xp.h
index aac9beb..c6a7d74 100644
--- a/arch/arm/mach-mvebu/armada-370-xp.h
+++ b/arch/arm/mach-mvebu/armada-370-xp.h
@@ -19,4 +19,11 @@
 #define ARMADA_370_XP_REGS_VIRT_BASE	IOMEM(0xfeb00000)
 #define ARMADA_370_XP_REGS_SIZE		SZ_1M
 
+#ifdef CONFIG_SMP
+#include <linux/cpumask.h>
+
+void armada_mpic_send_doorbell(const struct cpumask *mask, unsigned int irq);
+void armada_xp_mpic_smp_cpu_init(void);
+#endif
+
 #endif /* __MACH_ARMADA_370_XP_H */
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
new file mode 100644
index 0000000..8278960
--- /dev/null
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -0,0 +1,155 @@
+/*
+ * Coherency fabric (Aurora) support for Armada 370 and XP platforms.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory Clement <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * The Armada 370 and Armada XP SOCs have a coherency fabric which is
+ * responsible for ensuring hardware coherency between all CPUs and between
+ * CPUs and I/O masters. This file initializes the coherency fabric and
+ * supplies basic routines for configuring and controlling hardware coherency
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include <linux/smp.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <asm/smp_plat.h>
+#include "armada-370-xp.h"
+
+/*
+ * Some functions in this file are called very early during SMP
+ * initialization. At that time the device tree framework is not yet
+ * ready, and it is not possible to get the register address to
+ * ioremap it. That's why the pointer below is given with an initial
+ * value matching its virtual mapping
+ */
+static void __iomem *coherency_base = ARMADA_370_XP_REGS_VIRT_BASE + 0x20200;
+static void __iomem *coherency_cpu_base;
+
+/* Coherency fabric registers */
+#define COHERENCY_FABRIC_CFG_OFFSET		   0x4
+
+#define IO_SYNC_BARRIER_CTL_OFFSET		   0x0
+
+static struct of_device_id of_coherency_table[] = {
+	{.compatible = "marvell,coherency-fabric"},
+	{ /* end of list */ },
+};
+
+#ifdef CONFIG_SMP
+int coherency_get_cpu_count(void)
+{
+	int reg, cnt;
+
+	reg = readl(coherency_base + COHERENCY_FABRIC_CFG_OFFSET);
+	cnt = (reg & 0xF) + 1;
+
+	return cnt;
+}
+#endif
+
+/* Function defined in coherency_ll.S */
+int ll_set_cpu_coherent(void __iomem *base_addr, unsigned int hw_cpu_id);
+
+int set_cpu_coherent(unsigned int hw_cpu_id, int smp_group_id)
+{
+	if (!coherency_base) {
+		pr_warn("Can't make CPU %d cache coherent.\n", hw_cpu_id);
+		pr_warn("Coherency fabric is not initialized\n");
+		return 1;
+	}
+
+	return ll_set_cpu_coherent(coherency_base, hw_cpu_id);
+}
+
+static inline void mvebu_hwcc_sync_io_barrier(void)
+{
+	writel(0x1, coherency_cpu_base + IO_SYNC_BARRIER_CTL_OFFSET);
+	while (readl(coherency_cpu_base + IO_SYNC_BARRIER_CTL_OFFSET) & 0x1);
+}
+
+static dma_addr_t mvebu_hwcc_dma_map_page(struct device *dev, struct page *page,
+				  unsigned long offset, size_t size,
+				  enum dma_data_direction dir,
+				  struct dma_attrs *attrs)
+{
+	if (dir != DMA_TO_DEVICE)
+		mvebu_hwcc_sync_io_barrier();
+	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
+}
+
+
+static void mvebu_hwcc_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+			      size_t size, enum dma_data_direction dir,
+			      struct dma_attrs *attrs)
+{
+	if (dir != DMA_TO_DEVICE)
+		mvebu_hwcc_sync_io_barrier();
+}
+
+static void mvebu_hwcc_dma_sync(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir)
+{
+	if (dir != DMA_TO_DEVICE)
+		mvebu_hwcc_sync_io_barrier();
+}
+
+static struct dma_map_ops mvebu_hwcc_dma_ops = {
+	.alloc			= arm_dma_alloc,
+	.free			= arm_dma_free,
+	.mmap			= arm_dma_mmap,
+	.map_page		= mvebu_hwcc_dma_map_page,
+	.unmap_page		= mvebu_hwcc_dma_unmap_page,
+	.get_sgtable		= arm_dma_get_sgtable,
+	.map_sg			= arm_dma_map_sg,
+	.unmap_sg		= arm_dma_unmap_sg,
+	.sync_single_for_cpu	= mvebu_hwcc_dma_sync,
+	.sync_single_for_device	= mvebu_hwcc_dma_sync,
+	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
+	.set_dma_mask		= arm_dma_set_mask,
+};
+
+static int mvebu_hwcc_platform_notifier(struct notifier_block *nb,
+				       unsigned long event, void *__dev)
+{
+	struct device *dev = __dev;
+
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
+	set_dma_ops(dev, &mvebu_hwcc_dma_ops);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block mvebu_hwcc_platform_nb = {
+	.notifier_call = mvebu_hwcc_platform_notifier,
+};
+
+int __init coherency_init(void)
+{
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, of_coherency_table);
+	if (np) {
+		pr_info("Initializing Coherency fabric\n");
+		coherency_base = of_iomap(np, 0);
+		coherency_cpu_base = of_iomap(np, 1);
+		set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
+		bus_register_notifier(&platform_bus_type,
+					&mvebu_hwcc_platform_nb);
+	}
+
+	return 0;
+}
diff --git a/arch/arm/mach-mvebu/coherency.h b/arch/arm/mach-mvebu/coherency.h
new file mode 100644
index 0000000..2f42813
--- /dev/null
+++ b/arch/arm/mach-mvebu/coherency.h
@@ -0,0 +1,24 @@
+/*
+ * arch/arm/mach-mvebu/include/mach/coherency.h
+ *
+ *
+ * Coherency fabric (Aurora) support for Armada 370 and XP platforms.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MACH_370_XP_COHERENCY_H
+#define __MACH_370_XP_COHERENCY_H
+
+#ifdef CONFIG_SMP
+int coherency_get_cpu_count(void);
+#endif
+
+int set_cpu_coherent(int cpu_id, int smp_group_id);
+int coherency_init(void);
+
+#endif	/* __MACH_370_XP_COHERENCY_H */
diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
new file mode 100644
index 0000000..53e8391
--- /dev/null
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -0,0 +1,49 @@
+/*
+ * Coherency fabric: low level functions
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * This file implements the assembly function to add a CPU to the
+ * coherency fabric. This function is called by each of the secondary
+ * CPUs during their early boot in an SMP kernel, this why this
+ * function have to callable from assembly. It can also be called by a
+ * primary CPU from C code during its boot.
+ */
+
+#include <linux/linkage.h>
+#define ARMADA_XP_CFB_CTL_REG_OFFSET 0x0
+#define ARMADA_XP_CFB_CFG_REG_OFFSET 0x4
+
+	.text
+/*
+ * r0: Coherency fabric base register address
+ * r1: HW CPU id
+ */
+ENTRY(ll_set_cpu_coherent)
+	/* Create bit by cpu index */
+	mov	r3, #(1 << 24)
+	lsl	r1, r3, r1
+
+	/* Add CPU to SMP group - Atomic */
+	add	r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET
+	ldr	r2, [r3]
+	orr	r2, r2, r1
+	str	r2, [r3]
+
+	/* Enable coherency on CPU - Atomic */
+	add	r3, r0, #ARMADA_XP_CFB_CFG_REG_OFFSET
+	ldr	r2, [r3]
+	orr	r2, r2, r1
+	str	r2, [r3]
+
+	dsb
+
+	mov	r0, #0
+	mov	pc, lr
+ENDPROC(ll_set_cpu_coherent)
diff --git a/arch/arm/mach-mvebu/common.h b/arch/arm/mach-mvebu/common.h
index 02f89ea..aa27bc2 100644
--- a/arch/arm/mach-mvebu/common.h
+++ b/arch/arm/mach-mvebu/common.h
@@ -20,4 +20,9 @@ void mvebu_restart(char mode, const char *cmd);
 void armada_370_xp_init_irq(void);
 void armada_370_xp_handle_irq(struct pt_regs *regs);
 
+void armada_xp_cpu_die(unsigned int cpu);
+int armada_370_xp_coherency_init(void);
+int armada_370_xp_pmsu_init(void);
+void armada_xp_secondary_startup(void);
+extern struct smp_operations armada_xp_smp_ops;
 #endif
diff --git a/arch/arm/mach-mvebu/headsmp.S b/arch/arm/mach-mvebu/headsmp.S
new file mode 100644
index 0000000..a06e0ed
--- /dev/null
+++ b/arch/arm/mach-mvebu/headsmp.S
@@ -0,0 +1,49 @@
+/*
+ * SMP support: Entry point for secondary CPUs
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * This file implements the assembly entry point for secondary CPUs in
+ * an SMP kernel. The only thing we need to do is to add the CPU to
+ * the coherency fabric by writing to 2 registers. Currently the base
+ * register addresses are hard coded due to the early initialisation
+ * problems.
+ */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+/*
+ * At this stage the secondary CPUs don't have acces yet to the MMU, so
+ * we have to provide physical addresses
+ */
+#define ARMADA_XP_CFB_BASE	     0xD0020200
+
+	__CPUINIT
+
+/*
+ * Armada XP specific entry point for secondary CPUs.
+ * We add the CPU to the coherency fabric and then jump to secondary
+ * startup
+ */
+ENTRY(armada_xp_secondary_startup)
+
+	/* Read CPU id */
+	mrc     p15, 0, r1, c0, c0, 5
+	and     r1, r1, #0xF
+
+	/* Add CPU to coherency fabric */
+	ldr     r0, =ARMADA_XP_CFB_BASE
+
+	bl	ll_set_cpu_coherent
+	b	secondary_startup
+
+ENDPROC(armada_xp_secondary_startup)
diff --git a/arch/arm/mach-mvebu/hotplug.c b/arch/arm/mach-mvebu/hotplug.c
new file mode 100644
index 0000000..b228b6a
--- /dev/null
+++ b/arch/arm/mach-mvebu/hotplug.c
@@ -0,0 +1,30 @@
+/*
+ * Symmetric Multi Processing (SMP) support for Armada XP
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Lior Amsalem <alior@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/smp.h>
+#include <asm/proc-fns.h>
+
+/*
+ * platform-specific code to shutdown a CPU
+ *
+ * Called with IRQs disabled
+ */
+void __ref armada_xp_cpu_die(unsigned int cpu)
+{
+	cpu_do_idle();
+
+	/* We should never return from idle */
+	panic("mvebu: cpu %d unexpectedly exit from shutdown\n", cpu);
+}
diff --git a/arch/arm/mach-mvebu/irq-armada-370-xp.c b/arch/arm/mach-mvebu/irq-armada-370-xp.c
index 5f5f939..8e3fb08 100644
--- a/arch/arm/mach-mvebu/irq-armada-370-xp.c
+++ b/arch/arm/mach-mvebu/irq-armada-370-xp.c
@@ -24,6 +24,8 @@
 #include <linux/irqdomain.h>
 #include <asm/mach/arch.h>
 #include <asm/exception.h>
+#include <asm/smp_plat.h>
+#include <asm/hardware/cache-l2x0.h>
 
 /* Interrupt Controller Registers Map */
 #define ARMADA_370_XP_INT_SET_MASK_OFFS		(0x48)
@@ -35,6 +37,12 @@
 
 #define ARMADA_370_XP_CPU_INTACK_OFFS		(0x44)
 
+#define ARMADA_370_XP_SW_TRIG_INT_OFFS           (0x4)
+#define ARMADA_370_XP_IN_DRBEL_MSK_OFFS          (0xc)
+#define ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS        (0x8)
+
+#define ACTIVE_DOORBELLS			(8)
+
 static void __iomem *per_cpu_int_base;
 static void __iomem *main_int_base;
 static struct irq_domain *armada_370_xp_mpic_domain;
@@ -51,11 +59,22 @@ static void armada_370_xp_irq_unmask(struct irq_data *d)
 	       per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
 }
 
+#ifdef CONFIG_SMP
+static int armada_xp_set_affinity(struct irq_data *d,
+				  const struct cpumask *mask_val, bool force)
+{
+	return 0;
+}
+#endif
+
 static struct irq_chip armada_370_xp_irq_chip = {
 	.name		= "armada_370_xp_irq",
 	.irq_mask       = armada_370_xp_irq_mask,
 	.irq_mask_ack   = armada_370_xp_irq_mask,
 	.irq_unmask     = armada_370_xp_irq_unmask,
+#ifdef CONFIG_SMP
+	.irq_set_affinity = armada_xp_set_affinity,
+#endif
 };
 
 static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
@@ -72,6 +91,41 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
 	return 0;
 }
 
+#ifdef CONFIG_SMP
+void armada_mpic_send_doorbell(const struct cpumask *mask, unsigned int irq)
+{
+	int cpu;
+	unsigned long map = 0;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	dsb();
+
+	/* submit softirq */
+	writel((map << 8) | irq, main_int_base +
+		ARMADA_370_XP_SW_TRIG_INT_OFFS);
+}
+
+void armada_xp_mpic_smp_cpu_init(void)
+{
+	/* Clear pending IPIs */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
+
+	/* Enable first 8 IPIs */
+	writel((1 << ACTIVE_DOORBELLS) - 1, per_cpu_int_base +
+		ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+
+	/* Unmask IPI interrupt */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+}
+#endif /* CONFIG_SMP */
+
 static struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
 	.map = armada_370_xp_mpic_irq_map,
 	.xlate = irq_domain_xlate_onecell,
@@ -91,13 +145,18 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 	control = readl(main_int_base + ARMADA_370_XP_INT_CONTROL);
 
 	armada_370_xp_mpic_domain =
-	    irq_domain_add_linear(node, (control >> 2) & 0x3ff,
-				  &armada_370_xp_mpic_irq_ops, NULL);
+		irq_domain_add_linear(node, (control >> 2) & 0x3ff,
+				&armada_370_xp_mpic_irq_ops, NULL);
 
 	if (!armada_370_xp_mpic_domain)
 		panic("Unable to add Armada_370_Xp MPIC irq domain (DT)\n");
 
 	irq_set_default_host(armada_370_xp_mpic_domain);
+
+#ifdef CONFIG_SMP
+	armada_xp_mpic_smp_cpu_init();
+#endif
+
 	return 0;
 }
 
@@ -111,14 +170,36 @@ asmlinkage void __exception_irq_entry armada_370_xp_handle_irq(struct pt_regs
 					ARMADA_370_XP_CPU_INTACK_OFFS);
 		irqnr = irqstat & 0x3FF;
 
-		if (irqnr < 1023) {
-			irqnr =
-			    irq_find_mapping(armada_370_xp_mpic_domain, irqnr);
+		if (irqnr > 1022)
+			break;
+
+		if (irqnr >= 8) {
+			irqnr =	irq_find_mapping(armada_370_xp_mpic_domain,
+					irqnr);
 			handle_IRQ(irqnr, regs);
 			continue;
 		}
+#ifdef CONFIG_SMP
+		/* IPI Handling */
+		if (irqnr == 0) {
+			u32 ipimask, ipinr;
+
+			ipimask = readl_relaxed(per_cpu_int_base +
+						ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
+				& 0xFF;
+
+			writel(0x0, per_cpu_int_base +
+				ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
+
+			/* Handle all pending doorbells */
+			for (ipinr = 0; ipinr < ACTIVE_DOORBELLS; ipinr++) {
+				if (ipimask & (0x1 << ipinr))
+					handle_IPI(ipinr, regs);
+			}
+			continue;
+		}
+#endif
 
-		break;
 	} while (1);
 }
 
@@ -130,4 +211,7 @@ static const struct of_device_id mpic_of_match[] __initconst = {
 void __init armada_370_xp_init_irq(void)
 {
 	of_irq_init(mpic_of_match);
+#ifdef CONFIG_CACHE_L2X0
+	l2x0_of_init(0, ~0UL);
+#endif
 }
diff --git a/arch/arm/mach-mvebu/platsmp.c b/arch/arm/mach-mvebu/platsmp.c
new file mode 100644
index 0000000..fe16aaf
--- /dev/null
+++ b/arch/arm/mach-mvebu/platsmp.c
@@ -0,0 +1,122 @@
+/*
+ * Symmetric Multi Processing (SMP) support for Armada XP
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Lior Amsalem <alior@marvell.com>
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * The Armada XP SoC has 4 ARMv7 PJ4B CPUs running in full HW coherency
+ * This file implements the routines for preparing the SMP infrastructure
+ * and waking up the secondary CPUs
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include "common.h"
+#include "armada-370-xp.h"
+#include "pmsu.h"
+#include "coherency.h"
+
+void __init set_secondary_cpus_clock(void)
+{
+	int thiscpu;
+	unsigned long rate;
+	struct clk *cpu_clk = NULL;
+	struct device_node *np = NULL;
+
+	thiscpu = smp_processor_id();
+	for_each_node_by_type(np, "cpu") {
+		int err;
+		int cpu;
+
+		err = of_property_read_u32(np, "reg", &cpu);
+		if (WARN_ON(err))
+			return;
+
+		if (cpu == thiscpu) {
+			cpu_clk = of_clk_get(np, 0);
+			break;
+		}
+	}
+	if (WARN_ON(IS_ERR(cpu_clk)))
+		return;
+	clk_prepare_enable(cpu_clk);
+	rate = clk_get_rate(cpu_clk);
+
+	/* set all the other CPU clk to the same rate than the boot CPU */
+	for_each_node_by_type(np, "cpu") {
+		int err;
+		int cpu;
+
+		err = of_property_read_u32(np, "reg", &cpu);
+		if (WARN_ON(err))
+			return;
+
+		if (cpu != thiscpu) {
+			cpu_clk = of_clk_get(np, 0);
+			clk_set_rate(cpu_clk, rate);
+		}
+	}
+}
+
+static void __cpuinit armada_xp_secondary_init(unsigned int cpu)
+{
+	armada_xp_mpic_smp_cpu_init();
+}
+
+static int __cpuinit armada_xp_boot_secondary(unsigned int cpu,
+					      struct task_struct *idle)
+{
+	pr_info("Booting CPU %d\n", cpu);
+
+	armada_xp_boot_cpu(cpu, armada_xp_secondary_startup);
+
+	return 0;
+}
+
+static void __init armada_xp_smp_init_cpus(void)
+{
+	unsigned int i, ncores;
+	ncores = coherency_get_cpu_count();
+
+	/* Limit possible CPUs to defconfig */
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %d CPUs physically present. Only %d configured.",
+			ncores, nr_cpu_ids);
+		pr_warn("Clipping CPU count to %d\n", nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
+	for (i = 0; i < ncores; i++)
+		set_cpu_possible(i, true);
+
+	set_smp_cross_call(armada_mpic_send_doorbell);
+}
+
+void __init armada_xp_smp_prepare_cpus(unsigned int max_cpus)
+{
+	set_secondary_cpus_clock();
+	flush_cache_all();
+	set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
+}
+
+struct smp_operations armada_xp_smp_ops __initdata = {
+	.smp_init_cpus		= armada_xp_smp_init_cpus,
+	.smp_prepare_cpus	= armada_xp_smp_prepare_cpus,
+	.smp_secondary_init	= armada_xp_secondary_init,
+	.smp_boot_secondary	= armada_xp_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_die		= armada_xp_cpu_die,
+#endif
+};
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
new file mode 100644
index 0000000..3cc4bef
--- /dev/null
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -0,0 +1,75 @@
+/*
+ * Power Management Service Unit(PMSU) support for Armada 370/XP platforms.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory Clement <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * The Armada 370 and Armada XP SOCs have a power management service
+ * unit which is responsible for powering down and waking up CPUs and
+ * other SOC units
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include <linux/smp.h>
+#include <asm/smp_plat.h>
+
+static void __iomem *pmsu_mp_base;
+static void __iomem *pmsu_reset_base;
+
+#define PMSU_BOOT_ADDR_REDIRECT_OFFSET(cpu)	((cpu * 0x100) + 0x24)
+#define PMSU_RESET_CTL_OFFSET(cpu)		(cpu * 0x8)
+
+static struct of_device_id of_pmsu_table[] = {
+	{.compatible = "marvell,armada-370-xp-pmsu"},
+	{ /* end of list */ },
+};
+
+#ifdef CONFIG_SMP
+int armada_xp_boot_cpu(unsigned int cpu_id, void *boot_addr)
+{
+	int reg, hw_cpu;
+
+	if (!pmsu_mp_base || !pmsu_reset_base) {
+		pr_warn("Can't boot CPU. PMSU is uninitialized\n");
+		return 1;
+	}
+
+	hw_cpu = cpu_logical_map(cpu_id);
+
+	writel(virt_to_phys(boot_addr), pmsu_mp_base +
+			PMSU_BOOT_ADDR_REDIRECT_OFFSET(hw_cpu));
+
+	/* Release CPU from reset by clearing reset bit*/
+	reg = readl(pmsu_reset_base + PMSU_RESET_CTL_OFFSET(hw_cpu));
+	reg &= (~0x1);
+	writel(reg, pmsu_reset_base + PMSU_RESET_CTL_OFFSET(hw_cpu));
+
+	return 0;
+}
+#endif
+
+int __init armada_370_xp_pmsu_init(void)
+{
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, of_pmsu_table);
+	if (np) {
+		pr_info("Initializing Power Management Service Unit\n");
+		pmsu_mp_base = of_iomap(np, 0);
+		pmsu_reset_base = of_iomap(np, 1);
+	}
+
+	return 0;
+}
+
+early_initcall(armada_370_xp_pmsu_init);
diff --git a/arch/arm/mach-mvebu/pmsu.h b/arch/arm/mach-mvebu/pmsu.h
new file mode 100644
index 0000000..07a737c
--- /dev/null
+++ b/arch/arm/mach-mvebu/pmsu.h
@@ -0,0 +1,16 @@
+/*
+ * Power Management Service Unit (PMSU) support for Armada 370/XP platforms.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MACH_MVEBU_PMSU_H
+#define __MACH_MVEBU_PMSU_H
+
+int armada_xp_boot_cpu(unsigned int cpu_id, void *phys_addr);
+
+#endif	/* __MACH_370_XP_PMSU_H */
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 94186b6..3fd629d 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -352,6 +352,10 @@ config CPU_PJ4
 	select ARM_THUMBEE
 	select CPU_V7
 
+config CPU_PJ4B
+	bool
+	select CPU_V7
+
 # ARMv6
 config CPU_V6
 	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 58bc3e4..5383bc0 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -124,8 +124,6 @@ static void arm_dma_sync_single_for_device(struct device *dev,
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
-static int arm_dma_set_mask(struct device *dev, u64 dma_mask);
-
 struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
@@ -971,7 +969,7 @@ int dma_supported(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_supported);
 
-static int arm_dma_set_mask(struct device *dev, u64 dma_mask)
+int arm_dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
 		return -EIO;
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 42cc833..350f6a7 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -169,6 +169,63 @@ __v7_ca15mp_setup:
 	orreq	r0, r0, r10			@ Enable CPU-specific SMP bits
 	mcreq	p15, 0, r0, c1, c0, 1
 #endif
+
+__v7_pj4b_setup:
+#ifdef CONFIG_CPU_PJ4B
+
+/* Auxiliary Debug Modes Control 1 Register */
+#define PJ4B_STATIC_BP (1 << 2) /* Enable Static BP */
+#define PJ4B_INTER_PARITY (1 << 8) /* Disable Internal Parity Handling */
+#define PJ4B_BCK_OFF_STREX (1 << 5) /* Enable the back off of STREX instr */
+#define PJ4B_CLEAN_LINE (1 << 16) /* Disable data transfer for clean line */
+
+/* Auxiliary Debug Modes Control 2 Register */
+#define PJ4B_FAST_LDR (1 << 23) /* Disable fast LDR */
+#define PJ4B_SNOOP_DATA (1 << 25) /* Do not interleave write and snoop data */
+#define PJ4B_CWF (1 << 27) /* Disable Critical Word First feature */
+#define PJ4B_OUTSDNG_NC (1 << 29) /* Disable outstanding non cacheable rqst */
+#define PJ4B_L1_REP_RR (1 << 30) /* L1 replacement - Strict round robin */
+#define PJ4B_AUX_DBG_CTRL2 (PJ4B_SNOOP_DATA | PJ4B_CWF |\
+			    PJ4B_OUTSDNG_NC | PJ4B_L1_REP_RR)
+
+/* Auxiliary Functional Modes Control Register 0 */
+#define PJ4B_SMP_CFB (1 << 1) /* Set SMP mode. Join the coherency fabric */
+#define PJ4B_L1_PAR_CHK (1 << 2) /* Support L1 parity checking */
+#define PJ4B_BROADCAST_CACHE (1 << 8) /* Broadcast Cache and TLB maintenance */
+
+/* Auxiliary Debug Modes Control 0 Register */
+#define PJ4B_WFI_WFE (1 << 22) /* WFI/WFE - serve the DVM and back to idle */
+
+	/* Auxiliary Debug Modes Control 1 Register */
+	mrc	p15, 1,	r0, c15, c1, 1
+	orr     r0, r0, #PJ4B_CLEAN_LINE
+	orr     r0, r0, #PJ4B_BCK_OFF_STREX
+	orr     r0, r0, #PJ4B_INTER_PARITY
+	bic	r0, r0, #PJ4B_STATIC_BP
+	mcr	p15, 1,	r0, c15, c1, 1
+
+	/* Auxiliary Debug Modes Control 2 Register */
+	mrc	p15, 1,	r0, c15, c1, 2
+	bic	r0, r0, #PJ4B_FAST_LDR
+	orr	r0, r0, #PJ4B_AUX_DBG_CTRL2
+	mcr	p15, 1,	r0, c15, c1, 2
+
+	/* Auxiliary Functional Modes Control Register 0 */
+	mrc	p15, 1,	r0, c15, c2, 0
+#ifdef CONFIG_SMP
+	orr	r0, r0, #PJ4B_SMP_CFB
+#endif
+	orr	r0, r0, #PJ4B_L1_PAR_CHK
+	orr	r0, r0, #PJ4B_BROADCAST_CACHE
+	mcr	p15, 1,	r0, c15, c2, 0
+
+	/* Auxiliary Debug Modes Control 0 Register */
+	mrc	p15, 1,	r0, c15, c1, 0
+	orr	r0, r0, #PJ4B_WFI_WFE
+	mcr	p15, 1,	r0, c15, c1, 0
+
+#endif /* CONFIG_CPU_PJ4B */
+
 __v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
@@ -342,6 +399,16 @@ __v7_ca9mp_proc_info:
 	.long	0xff0ffff0
 	__v7_proc __v7_ca9mp_setup
 	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+
+	/*
+	 * Marvell PJ4B processor.
+	 */
+	.type   __v7_pj4b_proc_info, #object
+__v7_pj4b_proc_info:
+	.long	0x562f5840
+	.long	0xfffffff0
+	__v7_proc __v7_pj4b_setup
+	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
 #endif	/* CONFIG_ARM_LPAE */
 
 	/*
diff --git a/arch/arm/plat-orion/addr-map.c b/arch/arm/plat-orion/addr-map.c
index a7b8060..febe386 100644
--- a/arch/arm/plat-orion/addr-map.c
+++ b/arch/arm/plat-orion/addr-map.c
@@ -42,6 +42,8 @@ EXPORT_SYMBOL_GPL(mv_mbus_dram_info);
 #define WIN_REMAP_LO_OFF	0x0008
 #define WIN_REMAP_HI_OFF	0x000c
 
+#define ATTR_HW_COHERENCY	(0x1 << 4)
+
 /*
  * Default implementation
  */
@@ -163,6 +165,8 @@ void __init orion_setup_cpu_mbus_target(const struct orion_addr_map_cfg *cfg,
 			w = &orion_mbus_dram_info.cs[cs++];
 			w->cs_index = i;
 			w->mbus_attr = 0xf & ~(1 << i);
+			if (cfg->hw_io_coherency)
+				w->mbus_attr |= ATTR_HW_COHERENCY;
 			w->base = base & 0xffff0000;
 			w->size = (size | 0x0000ffff) + 1;
 		}
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index b8a688c..2d4b641 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -606,26 +606,6 @@ void __init orion_wdt_init(void)
  ****************************************************************************/
 static u64 orion_xor_dmamask = DMA_BIT_MASK(32);
 
-void __init orion_xor_init_channels(
-	struct mv_xor_platform_data *orion_xor0_data,
-	struct platform_device *orion_xor0_channel,
-	struct mv_xor_platform_data *orion_xor1_data,
-	struct platform_device *orion_xor1_channel)
-{
-	/*
-	 * two engines can't do memset simultaneously, this limitation
-	 * satisfied by removing memset support from one of the engines.
-	 */
-	dma_cap_set(DMA_MEMCPY, orion_xor0_data->cap_mask);
-	dma_cap_set(DMA_XOR, orion_xor0_data->cap_mask);
-	platform_device_register(orion_xor0_channel);
-
-	dma_cap_set(DMA_MEMCPY, orion_xor1_data->cap_mask);
-	dma_cap_set(DMA_MEMSET, orion_xor1_data->cap_mask);
-	dma_cap_set(DMA_XOR, orion_xor1_data->cap_mask);
-	platform_device_register(orion_xor1_channel);
-}
-
 /*****************************************************************************
  * XOR0
  ****************************************************************************/
@@ -636,61 +616,30 @@ static struct resource orion_xor0_shared_resources[] = {
 	}, {
 		.name	= "xor 0 high",
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.name   = "irq channel 0",
+		.flags  = IORESOURCE_IRQ,
+	}, {
+		.name   = "irq channel 1",
+		.flags  = IORESOURCE_IRQ,
 	},
 };
 
-static struct platform_device orion_xor0_shared = {
-	.name		= MV_XOR_SHARED_NAME,
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(orion_xor0_shared_resources),
-	.resource	= orion_xor0_shared_resources,
-};
+static struct mv_xor_channel_data orion_xor0_channels_data[2];
 
-static struct resource orion_xor00_resources[] = {
-	[0] = {
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct mv_xor_platform_data orion_xor00_data = {
-	.shared		= &orion_xor0_shared,
-	.hw_id		= 0,
-	.pool_size	= PAGE_SIZE,
+static struct mv_xor_platform_data orion_xor0_pdata = {
+	.channels = orion_xor0_channels_data,
 };
 
-static struct platform_device orion_xor00_channel = {
+static struct platform_device orion_xor0_shared = {
 	.name		= MV_XOR_NAME,
 	.id		= 0,
-	.num_resources	= ARRAY_SIZE(orion_xor00_resources),
-	.resource	= orion_xor00_resources,
-	.dev		= {
-		.dma_mask		= &orion_xor_dmamask,
-		.coherent_dma_mask	= DMA_BIT_MASK(64),
-		.platform_data		= &orion_xor00_data,
-	},
-};
-
-static struct resource orion_xor01_resources[] = {
-	[0] = {
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct mv_xor_platform_data orion_xor01_data = {
-	.shared		= &orion_xor0_shared,
-	.hw_id		= 1,
-	.pool_size	= PAGE_SIZE,
-};
-
-static struct platform_device orion_xor01_channel = {
-	.name		= MV_XOR_NAME,
-	.id		= 1,
-	.num_resources	= ARRAY_SIZE(orion_xor01_resources),
-	.resource	= orion_xor01_resources,
-	.dev		= {
-		.dma_mask		= &orion_xor_dmamask,
-		.coherent_dma_mask	= DMA_BIT_MASK(64),
-		.platform_data		= &orion_xor01_data,
+	.num_resources	= ARRAY_SIZE(orion_xor0_shared_resources),
+	.resource	= orion_xor0_shared_resources,
+	.dev            = {
+		.dma_mask               = &orion_xor_dmamask,
+		.coherent_dma_mask      = DMA_BIT_MASK(64),
+		.platform_data          = &orion_xor0_pdata,
 	},
 };
 
@@ -704,15 +653,23 @@ void __init orion_xor0_init(unsigned long mapbase_low,
 	orion_xor0_shared_resources[1].start = mapbase_high;
 	orion_xor0_shared_resources[1].end = mapbase_high + 0xff;
 
-	orion_xor00_resources[0].start = irq_0;
-	orion_xor00_resources[0].end = irq_0;
-	orion_xor01_resources[0].start = irq_1;
-	orion_xor01_resources[0].end = irq_1;
+	orion_xor0_shared_resources[2].start = irq_0;
+	orion_xor0_shared_resources[2].end = irq_0;
+	orion_xor0_shared_resources[3].start = irq_1;
+	orion_xor0_shared_resources[3].end = irq_1;
 
-	platform_device_register(&orion_xor0_shared);
+	/*
+	 * two engines can't do memset simultaneously, this limitation
+	 * satisfied by removing memset support from one of the engines.
+	 */
+	dma_cap_set(DMA_MEMCPY, orion_xor0_channels_data[0].cap_mask);
+	dma_cap_set(DMA_XOR, orion_xor0_channels_data[0].cap_mask);
+
+	dma_cap_set(DMA_MEMSET, orion_xor0_channels_data[1].cap_mask);
+	dma_cap_set(DMA_MEMCPY, orion_xor0_channels_data[1].cap_mask);
+	dma_cap_set(DMA_XOR, orion_xor0_channels_data[1].cap_mask);
 
-	orion_xor_init_channels(&orion_xor00_data, &orion_xor00_channel,
-				&orion_xor01_data, &orion_xor01_channel);
+	platform_device_register(&orion_xor0_shared);
 }
 
 /*****************************************************************************
@@ -725,61 +682,30 @@ static struct resource orion_xor1_shared_resources[] = {
 	}, {
 		.name	= "xor 1 high",
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.name   = "irq channel 0",
+		.flags  = IORESOURCE_IRQ,
+	}, {
+		.name   = "irq channel 1",
+		.flags  = IORESOURCE_IRQ,
 	},
 };
 
-static struct platform_device orion_xor1_shared = {
-	.name		= MV_XOR_SHARED_NAME,
-	.id		= 1,
-	.num_resources	= ARRAY_SIZE(orion_xor1_shared_resources),
-	.resource	= orion_xor1_shared_resources,
-};
-
-static struct resource orion_xor10_resources[] = {
-	[0] = {
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct mv_xor_platform_data orion_xor10_data = {
-	.shared		= &orion_xor1_shared,
-	.hw_id		= 0,
-	.pool_size	= PAGE_SIZE,
-};
-
-static struct platform_device orion_xor10_channel = {
-	.name		= MV_XOR_NAME,
-	.id		= 2,
-	.num_resources	= ARRAY_SIZE(orion_xor10_resources),
-	.resource	= orion_xor10_resources,
-	.dev		= {
-		.dma_mask		= &orion_xor_dmamask,
-		.coherent_dma_mask	= DMA_BIT_MASK(64),
-		.platform_data		= &orion_xor10_data,
-	},
-};
-
-static struct resource orion_xor11_resources[] = {
-	[0] = {
-		.flags	= IORESOURCE_IRQ,
-	},
-};
+static struct mv_xor_channel_data orion_xor1_channels_data[2];
 
-static struct mv_xor_platform_data orion_xor11_data = {
-	.shared		= &orion_xor1_shared,
-	.hw_id		= 1,
-	.pool_size	= PAGE_SIZE,
+static struct mv_xor_platform_data orion_xor1_pdata = {
+	.channels = orion_xor1_channels_data,
 };
 
-static struct platform_device orion_xor11_channel = {
+static struct platform_device orion_xor1_shared = {
 	.name		= MV_XOR_NAME,
-	.id		= 3,
-	.num_resources	= ARRAY_SIZE(orion_xor11_resources),
-	.resource	= orion_xor11_resources,
-	.dev		= {
-		.dma_mask		= &orion_xor_dmamask,
-		.coherent_dma_mask	= DMA_BIT_MASK(64),
-		.platform_data		= &orion_xor11_data,
+	.id		= 1,
+	.num_resources	= ARRAY_SIZE(orion_xor1_shared_resources),
+	.resource	= orion_xor1_shared_resources,
+	.dev            = {
+		.dma_mask               = &orion_xor_dmamask,
+		.coherent_dma_mask      = DMA_BIT_MASK(64),
+		.platform_data          = &orion_xor1_pdata,
 	},
 };
 
@@ -793,15 +719,23 @@ void __init orion_xor1_init(unsigned long mapbase_low,
 	orion_xor1_shared_resources[1].start = mapbase_high;
 	orion_xor1_shared_resources[1].end = mapbase_high + 0xff;
 
-	orion_xor10_resources[0].start = irq_0;
-	orion_xor10_resources[0].end = irq_0;
-	orion_xor11_resources[0].start = irq_1;
-	orion_xor11_resources[0].end = irq_1;
+	orion_xor1_shared_resources[2].start = irq_0;
+	orion_xor1_shared_resources[2].end = irq_0;
+	orion_xor1_shared_resources[3].start = irq_1;
+	orion_xor1_shared_resources[3].end = irq_1;
 
-	platform_device_register(&orion_xor1_shared);
+	/*
+	 * two engines can't do memset simultaneously, this limitation
+	 * satisfied by removing memset support from one of the engines.
+	 */
+	dma_cap_set(DMA_MEMCPY, orion_xor1_channels_data[0].cap_mask);
+	dma_cap_set(DMA_XOR, orion_xor1_channels_data[0].cap_mask);
 
-	orion_xor_init_channels(&orion_xor10_data, &orion_xor10_channel,
-				&orion_xor11_data, &orion_xor11_channel);
+	dma_cap_set(DMA_MEMSET, orion_xor1_channels_data[1].cap_mask);
+	dma_cap_set(DMA_MEMCPY, orion_xor1_channels_data[1].cap_mask);
+	dma_cap_set(DMA_XOR, orion_xor1_channels_data[1].cap_mask);
+
+	platform_device_register(&orion_xor1_shared);
 }
 
 /*****************************************************************************
diff --git a/arch/arm/plat-orion/include/plat/addr-map.h b/arch/arm/plat-orion/include/plat/addr-map.h
index ec63e4a..b76c065 100644
--- a/arch/arm/plat-orion/include/plat/addr-map.h
+++ b/arch/arm/plat-orion/include/plat/addr-map.h
@@ -17,6 +17,7 @@ struct orion_addr_map_cfg {
 	const int num_wins;	/* Total number of windows */
 	const int remappable_wins;
 	void __iomem *bridge_virt_base;
+	int hw_io_coherency;
 
 	/* If NULL, the default cpu_win_can_remap will be used, using
 	   the value in remappable_wins */
diff --git a/arch/arm/plat-orion/include/plat/common.h b/arch/arm/plat-orion/include/plat/common.h
index 6bbc3fe..e06fc5f 100644
--- a/arch/arm/plat-orion/include/plat/common.h
+++ b/arch/arm/plat-orion/include/plat/common.h
@@ -12,6 +12,7 @@
 #include <linux/mv643xx_eth.h>
 
 struct dsa_platform_data;
+struct mv_sata_platform_data;
 
 void __init orion_uart0_init(void __iomem *membase,
 			     resource_size_t mapbase,
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 823f62d..a47e6ee 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -64,3 +64,5 @@ config CLK_TWL6040
 	  as functional clock.
 
 endmenu
+
+source "drivers/clk/mvebu/Kconfig"
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 4e1ccb1..ee90e87 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_PLAT_SPEAR)	+= spear/
 obj-$(CONFIG_ARCH_U300)		+= clk-u300.o
 obj-$(CONFIG_COMMON_CLK_VERSATILE) += versatile/
 obj-$(CONFIG_ARCH_PRIMA2)	+= clk-prima2.o
+obj-$(CONFIG_PLAT_ORION)	+= mvebu/
 ifeq ($(CONFIG_COMMON_CLK), y)
 obj-$(CONFIG_ARCH_MMP)		+= mmp/
 endif
diff --git a/drivers/clk/mvebu/Kconfig b/drivers/clk/mvebu/Kconfig
new file mode 100644
index 0000000..57323fd
--- /dev/null
+++ b/drivers/clk/mvebu/Kconfig
@@ -0,0 +1,8 @@
+config MVEBU_CLK_CORE
+       bool
+
+config MVEBU_CLK_CPU
+       bool
+
+config MVEBU_CLK_GATING
+       bool
diff --git a/drivers/clk/mvebu/Makefile b/drivers/clk/mvebu/Makefile
new file mode 100644
index 0000000..58df3dc
--- /dev/null
+++ b/drivers/clk/mvebu/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_MVEBU_CLK_CORE) 	+= clk.o clk-core.o
+obj-$(CONFIG_MVEBU_CLK_CPU) 	+= clk-cpu.o
+obj-$(CONFIG_MVEBU_CLK_GATING) 	+= clk-gating-ctrl.o
diff --git a/drivers/clk/mvebu/clk-core.c b/drivers/clk/mvebu/clk-core.c
new file mode 100644
index 0000000..69056a7
--- /dev/null
+++ b/drivers/clk/mvebu/clk-core.c
@@ -0,0 +1,675 @@
+/*
+ * Marvell EBU clock core handling defined at reset
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include "clk-core.h"
+
+struct core_ratio {
+	int id;
+	const char *name;
+};
+
+struct core_clocks {
+	u32 (*get_tclk_freq)(void __iomem *sar);
+	u32 (*get_cpu_freq)(void __iomem *sar);
+	void (*get_clk_ratio)(void __iomem *sar, int id, int *mult, int *div);
+	const struct core_ratio *ratios;
+	int num_ratios;
+};
+
+static struct clk_onecell_data clk_data;
+
+static void __init mvebu_clk_core_setup(struct device_node *np,
+				 struct core_clocks *coreclk)
+{
+	const char *tclk_name = "tclk";
+	const char *cpuclk_name = "cpuclk";
+	void __iomem *base;
+	unsigned long rate;
+	int n;
+
+	base = of_iomap(np, 0);
+	if (WARN_ON(!base))
+		return;
+
+	/*
+	 * Allocate struct for TCLK, cpu clk, and core ratio clocks
+	 */
+	clk_data.clk_num = 2 + coreclk->num_ratios;
+	clk_data.clks = kzalloc(clk_data.clk_num * sizeof(struct clk *),
+				GFP_KERNEL);
+	if (WARN_ON(!clk_data.clks))
+		return;
+
+	/*
+	 * Register TCLK
+	 */
+	of_property_read_string_index(np, "clock-output-names", 0,
+				      &tclk_name);
+	rate = coreclk->get_tclk_freq(base);
+	clk_data.clks[0] = clk_register_fixed_rate(NULL, tclk_name, NULL,
+						   CLK_IS_ROOT, rate);
+	WARN_ON(IS_ERR(clk_data.clks[0]));
+
+	/*
+	 * Register CPU clock
+	 */
+	of_property_read_string_index(np, "clock-output-names", 1,
+				      &cpuclk_name);
+	rate = coreclk->get_cpu_freq(base);
+	clk_data.clks[1] = clk_register_fixed_rate(NULL, cpuclk_name, NULL,
+						   CLK_IS_ROOT, rate);
+	WARN_ON(IS_ERR(clk_data.clks[1]));
+
+	/*
+	 * Register fixed-factor clocks derived from CPU clock
+	 */
+	for (n = 0; n < coreclk->num_ratios; n++) {
+		const char *rclk_name = coreclk->ratios[n].name;
+		int mult, div;
+
+		of_property_read_string_index(np, "clock-output-names",
+					      2+n, &rclk_name);
+		coreclk->get_clk_ratio(base, coreclk->ratios[n].id,
+				       &mult, &div);
+		clk_data.clks[2+n] = clk_register_fixed_factor(NULL, rclk_name,
+				       cpuclk_name, 0, mult, div);
+		WARN_ON(IS_ERR(clk_data.clks[2+n]));
+	};
+
+	/*
+	 * SAR register isn't needed anymore
+	 */
+	iounmap(base);
+
+	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+}
+
+#ifdef CONFIG_MACH_ARMADA_370_XP
+/*
+ * Armada 370/XP Sample At Reset is a 64 bit bitfiled split in two
+ * register of 32 bits
+ */
+
+#define SARL				    0	/* Low part [0:31] */
+#define	    SARL_AXP_PCLK_FREQ_OPT	    21
+#define	    SARL_AXP_PCLK_FREQ_OPT_MASK	    0x7
+#define	    SARL_A370_PCLK_FREQ_OPT	    11
+#define	    SARL_A370_PCLK_FREQ_OPT_MASK    0xF
+#define	    SARL_AXP_FAB_FREQ_OPT	    24
+#define	    SARL_AXP_FAB_FREQ_OPT_MASK	    0xF
+#define	    SARL_A370_FAB_FREQ_OPT	    15
+#define	    SARL_A370_FAB_FREQ_OPT_MASK	    0x1F
+#define	    SARL_A370_TCLK_FREQ_OPT	    20
+#define	    SARL_A370_TCLK_FREQ_OPT_MASK    0x1
+#define SARH				    4	/* High part [32:63] */
+#define	    SARH_AXP_PCLK_FREQ_OPT	    (52-32)
+#define	    SARH_AXP_PCLK_FREQ_OPT_MASK	    0x1
+#define	    SARH_AXP_PCLK_FREQ_OPT_SHIFT    3
+#define	    SARH_AXP_FAB_FREQ_OPT	    (51-32)
+#define	    SARH_AXP_FAB_FREQ_OPT_MASK	    0x1
+#define	    SARH_AXP_FAB_FREQ_OPT_SHIFT	    4
+
+static const u32 __initconst armada_370_tclk_frequencies[] = {
+	16600000,
+	20000000,
+};
+
+static u32 __init armada_370_get_tclk_freq(void __iomem *sar)
+{
+	u8 tclk_freq_select = 0;
+
+	tclk_freq_select = ((readl(sar) >> SARL_A370_TCLK_FREQ_OPT) &
+			    SARL_A370_TCLK_FREQ_OPT_MASK);
+	return armada_370_tclk_frequencies[tclk_freq_select];
+}
+
+static const u32 __initconst armada_370_cpu_frequencies[] = {
+	400000000,
+	533000000,
+	667000000,
+	800000000,
+	1000000000,
+	1067000000,
+	1200000000,
+};
+
+static u32 __init armada_370_get_cpu_freq(void __iomem *sar)
+{
+	u32 cpu_freq;
+	u8 cpu_freq_select = 0;
+
+	cpu_freq_select = ((readl(sar) >> SARL_A370_PCLK_FREQ_OPT) &
+			   SARL_A370_PCLK_FREQ_OPT_MASK);
+	if (cpu_freq_select > ARRAY_SIZE(armada_370_cpu_frequencies)) {
+		pr_err("CPU freq select unsuported %d\n", cpu_freq_select);
+		cpu_freq = 0;
+	} else
+		cpu_freq = armada_370_cpu_frequencies[cpu_freq_select];
+
+	return cpu_freq;
+}
+
+enum { A370_XP_NBCLK, A370_XP_HCLK, A370_XP_DRAMCLK };
+
+static const struct core_ratio __initconst armada_370_xp_core_ratios[] = {
+	{ .id = A370_XP_NBCLK,	 .name = "nbclk" },
+	{ .id = A370_XP_HCLK,	 .name = "hclk" },
+	{ .id = A370_XP_DRAMCLK, .name = "dramclk" },
+};
+
+static const int __initconst armada_370_xp_nbclk_ratios[32][2] = {
+	{0, 1}, {1, 2}, {2, 2}, {2, 2},
+	{1, 2}, {1, 2}, {1, 1}, {2, 3},
+	{0, 1}, {1, 2}, {2, 4}, {0, 1},
+	{1, 2}, {0, 1}, {0, 1}, {2, 2},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{2, 3}, {0, 1}, {0, 1}, {0, 1},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{0, 1}, {0, 1}, {0, 1}, {0, 1},
+};
+
+static const int __initconst armada_370_xp_hclk_ratios[32][2] = {
+	{0, 1}, {1, 2}, {2, 6}, {2, 3},
+	{1, 3}, {1, 4}, {1, 2}, {2, 6},
+	{0, 1}, {1, 6}, {2, 10}, {0, 1},
+	{1, 4}, {0, 1}, {0, 1}, {2, 5},
+	{0, 1}, {0, 1}, {0, 1}, {1, 2},
+	{2, 6}, {0, 1}, {0, 1}, {0, 1},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{0, 1}, {0, 1}, {0, 1}, {0, 1},
+};
+
+static const int __initconst armada_370_xp_dramclk_ratios[32][2] = {
+	{0, 1}, {1, 2}, {2, 3}, {2, 3},
+	{1, 3}, {1, 2}, {1, 2}, {2, 6},
+	{0, 1}, {1, 3}, {2, 5}, {0, 1},
+	{1, 4}, {0, 1}, {0, 1}, {2, 5},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{2, 3}, {0, 1}, {0, 1}, {0, 1},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{0, 1}, {0, 1}, {0, 1}, {0, 1},
+};
+
+static void __init armada_370_xp_get_clk_ratio(u32 opt,
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	switch (id) {
+	case A370_XP_NBCLK:
+		*mult = armada_370_xp_nbclk_ratios[opt][0];
+		*div = armada_370_xp_nbclk_ratios[opt][1];
+		break;
+	case A370_XP_HCLK:
+		*mult = armada_370_xp_hclk_ratios[opt][0];
+		*div = armada_370_xp_hclk_ratios[opt][1];
+		break;
+	case A370_XP_DRAMCLK:
+		*mult = armada_370_xp_dramclk_ratios[opt][0];
+		*div = armada_370_xp_dramclk_ratios[opt][1];
+		break;
+	}
+}
+
+static void __init armada_370_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	u32 opt = ((readl(sar) >> SARL_A370_FAB_FREQ_OPT) &
+		SARL_A370_FAB_FREQ_OPT_MASK);
+
+	armada_370_xp_get_clk_ratio(opt, sar, id, mult, div);
+}
+
+
+static const struct core_clocks armada_370_core_clocks = {
+	.get_tclk_freq = armada_370_get_tclk_freq,
+	.get_cpu_freq = armada_370_get_cpu_freq,
+	.get_clk_ratio = armada_370_get_clk_ratio,
+	.ratios = armada_370_xp_core_ratios,
+	.num_ratios = ARRAY_SIZE(armada_370_xp_core_ratios),
+};
+
+static const u32 __initconst armada_xp_cpu_frequencies[] = {
+	1000000000,
+	1066000000,
+	1200000000,
+	1333000000,
+	1500000000,
+	1666000000,
+	1800000000,
+	2000000000,
+	667000000,
+	0,
+	800000000,
+	1600000000,
+};
+
+/* For Armada XP TCLK frequency is fix: 250MHz */
+static u32 __init armada_xp_get_tclk_freq(void __iomem *sar)
+{
+	return 250 * 1000 * 1000;
+}
+
+static u32 __init armada_xp_get_cpu_freq(void __iomem *sar)
+{
+	u32 cpu_freq;
+	u8 cpu_freq_select = 0;
+
+	cpu_freq_select = ((readl(sar) >> SARL_AXP_PCLK_FREQ_OPT) &
+			   SARL_AXP_PCLK_FREQ_OPT_MASK);
+	/*
+	 * The upper bit is not contiguous to the other ones and
+	 * located in the high part of the SAR registers
+	 */
+	cpu_freq_select |= (((readl(sar+4) >> SARH_AXP_PCLK_FREQ_OPT) &
+			     SARH_AXP_PCLK_FREQ_OPT_MASK)
+			    << SARH_AXP_PCLK_FREQ_OPT_SHIFT);
+	if (cpu_freq_select > ARRAY_SIZE(armada_xp_cpu_frequencies)) {
+		pr_err("CPU freq select unsuported: %d\n", cpu_freq_select);
+		cpu_freq = 0;
+	} else
+		cpu_freq = armada_xp_cpu_frequencies[cpu_freq_select];
+
+	return cpu_freq;
+}
+
+static void __init armada_xp_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+
+	u32 opt = ((readl(sar) >> SARL_AXP_FAB_FREQ_OPT) &
+	      SARL_AXP_FAB_FREQ_OPT_MASK);
+	/*
+	 * The upper bit is not contiguous to the other ones and
+	 * located in the high part of the SAR registers
+	 */
+	opt |= (((readl(sar+4) >> SARH_AXP_FAB_FREQ_OPT) &
+		SARH_AXP_FAB_FREQ_OPT_MASK)
+	       << SARH_AXP_FAB_FREQ_OPT_SHIFT);
+
+	armada_370_xp_get_clk_ratio(opt, sar, id, mult, div);
+}
+
+static const struct core_clocks armada_xp_core_clocks = {
+	.get_tclk_freq = armada_xp_get_tclk_freq,
+	.get_cpu_freq = armada_xp_get_cpu_freq,
+	.get_clk_ratio = armada_xp_get_clk_ratio,
+	.ratios = armada_370_xp_core_ratios,
+	.num_ratios = ARRAY_SIZE(armada_370_xp_core_ratios),
+};
+
+#endif /* CONFIG_MACH_ARMADA_370_XP */
+
+/*
+ * Dove PLL sample-at-reset configuration
+ *
+ * SAR0[8:5]   : CPU frequency
+ *		 5  = 1000 MHz
+ *		 6  =  933 MHz
+ *		 7  =  933 MHz
+ *		 8  =  800 MHz
+ *		 9  =  800 MHz
+ *		 10 =  800 MHz
+ *		 11 = 1067 MHz
+ *		 12 =  667 MHz
+ *		 13 =  533 MHz
+ *		 14 =  400 MHz
+ *		 15 =  333 MHz
+ *		 others reserved.
+ *
+ * SAR0[11:9]  : CPU to L2 Clock divider ratio
+ *		 0 = (1/1) * CPU
+ *		 2 = (1/2) * CPU
+ *		 4 = (1/3) * CPU
+ *		 6 = (1/4) * CPU
+ *		 others reserved.
+ *
+ * SAR0[15:12] : CPU to DDR DRAM Clock divider ratio
+ *		 0  = (1/1) * CPU
+ *		 2  = (1/2) * CPU
+ *		 3  = (2/5) * CPU
+ *		 4  = (1/3) * CPU
+ *		 6  = (1/4) * CPU
+ *		 8  = (1/5) * CPU
+ *		 10 = (1/6) * CPU
+ *		 12 = (1/7) * CPU
+ *		 14 = (1/8) * CPU
+ *		 15 = (1/10) * CPU
+ *		 others reserved.
+ *
+ * SAR0[24:23] : TCLK frequency
+ *		 0 = 166 MHz
+ *		 1 = 125 MHz
+ *		 others reserved.
+ */
+#ifdef CONFIG_ARCH_DOVE
+#define SAR_DOVE_CPU_FREQ		5
+#define SAR_DOVE_CPU_FREQ_MASK		0xf
+#define SAR_DOVE_L2_RATIO		9
+#define SAR_DOVE_L2_RATIO_MASK		0x7
+#define SAR_DOVE_DDR_RATIO		12
+#define SAR_DOVE_DDR_RATIO_MASK		0xf
+#define SAR_DOVE_TCLK_FREQ		23
+#define SAR_DOVE_TCLK_FREQ_MASK		0x3
+
+static const u32 __initconst dove_tclk_frequencies[] = {
+	166666667,
+	125000000,
+	0, 0
+};
+
+static u32 __init dove_get_tclk_freq(void __iomem *sar)
+{
+	u32 opt = (readl(sar) >> SAR_DOVE_TCLK_FREQ) &
+		SAR_DOVE_TCLK_FREQ_MASK;
+	return dove_tclk_frequencies[opt];
+}
+
+static const u32 __initconst dove_cpu_frequencies[] = {
+	0, 0, 0, 0, 0,
+	1000000000,
+	933333333, 933333333,
+	800000000, 800000000, 800000000,
+	1066666667,
+	666666667,
+	533333333,
+	400000000,
+	333333333
+};
+
+static u32 __init dove_get_cpu_freq(void __iomem *sar)
+{
+	u32 opt = (readl(sar) >> SAR_DOVE_CPU_FREQ) &
+		SAR_DOVE_CPU_FREQ_MASK;
+	return dove_cpu_frequencies[opt];
+}
+
+enum { DOVE_CPU_TO_L2, DOVE_CPU_TO_DDR };
+
+static const struct core_ratio __initconst dove_core_ratios[] = {
+	{ .id = DOVE_CPU_TO_L2, .name = "l2clk", },
+	{ .id = DOVE_CPU_TO_DDR, .name = "ddrclk", }
+};
+
+static const int __initconst dove_cpu_l2_ratios[8][2] = {
+	{ 1, 1 }, { 0, 1 }, { 1, 2 }, { 0, 1 },
+	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 0, 1 }
+};
+
+static const int __initconst dove_cpu_ddr_ratios[16][2] = {
+	{ 1, 1 }, { 0, 1 }, { 1, 2 }, { 2, 5 },
+	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 0, 1 },
+	{ 1, 5 }, { 0, 1 }, { 1, 6 }, { 0, 1 },
+	{ 1, 7 }, { 0, 1 }, { 1, 8 }, { 1, 10 }
+};
+
+static void __init dove_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	switch (id) {
+	case DOVE_CPU_TO_L2:
+	{
+		u32 opt = (readl(sar) >> SAR_DOVE_L2_RATIO) &
+			SAR_DOVE_L2_RATIO_MASK;
+		*mult = dove_cpu_l2_ratios[opt][0];
+		*div = dove_cpu_l2_ratios[opt][1];
+		break;
+	}
+	case DOVE_CPU_TO_DDR:
+	{
+		u32 opt = (readl(sar) >> SAR_DOVE_DDR_RATIO) &
+			SAR_DOVE_DDR_RATIO_MASK;
+		*mult = dove_cpu_ddr_ratios[opt][0];
+		*div = dove_cpu_ddr_ratios[opt][1];
+		break;
+	}
+	}
+}
+
+static const struct core_clocks dove_core_clocks = {
+	.get_tclk_freq = dove_get_tclk_freq,
+	.get_cpu_freq = dove_get_cpu_freq,
+	.get_clk_ratio = dove_get_clk_ratio,
+	.ratios = dove_core_ratios,
+	.num_ratios = ARRAY_SIZE(dove_core_ratios),
+};
+#endif /* CONFIG_ARCH_DOVE */
+
+/*
+ * Kirkwood PLL sample-at-reset configuration
+ * (6180 has different SAR layout than other Kirkwood SoCs)
+ *
+ * SAR0[4:3,22,1] : CPU frequency (6281,6292,6282)
+ *	4  =  600 MHz
+ *	6  =  800 MHz
+ *	7  = 1000 MHz
+ *	9  = 1200 MHz
+ *	12 = 1500 MHz
+ *	13 = 1600 MHz
+ *	14 = 1800 MHz
+ *	15 = 2000 MHz
+ *	others reserved.
+ *
+ * SAR0[19,10:9] : CPU to L2 Clock divider ratio (6281,6292,6282)
+ *	1 = (1/2) * CPU
+ *	3 = (1/3) * CPU
+ *	5 = (1/4) * CPU
+ *	others reserved.
+ *
+ * SAR0[8:5] : CPU to DDR DRAM Clock divider ratio (6281,6292,6282)
+ *	2 = (1/2) * CPU
+ *	4 = (1/3) * CPU
+ *	6 = (1/4) * CPU
+ *	7 = (2/9) * CPU
+ *	8 = (1/5) * CPU
+ *	9 = (1/6) * CPU
+ *	others reserved.
+ *
+ * SAR0[4:2] : Kirkwood 6180 cpu/l2/ddr clock configuration (6180 only)
+ *	5 = [CPU =  600 MHz, L2 = (1/2) * CPU, DDR = 200 MHz = (1/3) * CPU]
+ *	6 = [CPU =  800 MHz, L2 = (1/2) * CPU, DDR = 200 MHz = (1/4) * CPU]
+ *	7 = [CPU = 1000 MHz, L2 = (1/2) * CPU, DDR = 200 MHz = (1/5) * CPU]
+ *	others reserved.
+ *
+ * SAR0[21] : TCLK frequency
+ *	0 = 200 MHz
+ *	1 = 166 MHz
+ *	others reserved.
+ */
+#ifdef CONFIG_ARCH_KIRKWOOD
+#define SAR_KIRKWOOD_CPU_FREQ(x)	\
+	(((x & (1 <<  1)) >>  1) |	\
+	 ((x & (1 << 22)) >> 21) |	\
+	 ((x & (3 <<  3)) >>  1))
+#define SAR_KIRKWOOD_L2_RATIO(x)	\
+	(((x & (3 <<  9)) >> 9) |	\
+	 (((x & (1 << 19)) >> 17)))
+#define SAR_KIRKWOOD_DDR_RATIO		5
+#define SAR_KIRKWOOD_DDR_RATIO_MASK	0xf
+#define SAR_MV88F6180_CLK		2
+#define SAR_MV88F6180_CLK_MASK		0x7
+#define SAR_KIRKWOOD_TCLK_FREQ		21
+#define SAR_KIRKWOOD_TCLK_FREQ_MASK	0x1
+
+enum { KIRKWOOD_CPU_TO_L2, KIRKWOOD_CPU_TO_DDR };
+
+static const struct core_ratio __initconst kirkwood_core_ratios[] = {
+	{ .id = KIRKWOOD_CPU_TO_L2, .name = "l2clk", },
+	{ .id = KIRKWOOD_CPU_TO_DDR, .name = "ddrclk", }
+};
+
+static u32 __init kirkwood_get_tclk_freq(void __iomem *sar)
+{
+	u32 opt = (readl(sar) >> SAR_KIRKWOOD_TCLK_FREQ) &
+		SAR_KIRKWOOD_TCLK_FREQ_MASK;
+	return (opt) ? 166666667 : 200000000;
+}
+
+static const u32 __initconst kirkwood_cpu_frequencies[] = {
+	0, 0, 0, 0,
+	600000000,
+	0,
+	800000000,
+	1000000000,
+	0,
+	1200000000,
+	0, 0,
+	1500000000,
+	1600000000,
+	1800000000,
+	2000000000
+};
+
+static u32 __init kirkwood_get_cpu_freq(void __iomem *sar)
+{
+	u32 opt = SAR_KIRKWOOD_CPU_FREQ(readl(sar));
+	return kirkwood_cpu_frequencies[opt];
+}
+
+static const int __initconst kirkwood_cpu_l2_ratios[8][2] = {
+	{ 0, 1 }, { 1, 2 }, { 0, 1 }, { 1, 3 },
+	{ 0, 1 }, { 1, 4 }, { 0, 1 }, { 0, 1 }
+};
+
+static const int __initconst kirkwood_cpu_ddr_ratios[16][2] = {
+	{ 0, 1 }, { 0, 1 }, { 1, 2 }, { 0, 1 },
+	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 2, 9 },
+	{ 1, 5 }, { 1, 6 }, { 0, 1 }, { 0, 1 },
+	{ 0, 1 }, { 0, 1 }, { 0, 1 }, { 0, 1 }
+};
+
+static void __init kirkwood_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	switch (id) {
+	case KIRKWOOD_CPU_TO_L2:
+	{
+		u32 opt = SAR_KIRKWOOD_L2_RATIO(readl(sar));
+		*mult = kirkwood_cpu_l2_ratios[opt][0];
+		*div = kirkwood_cpu_l2_ratios[opt][1];
+		break;
+	}
+	case KIRKWOOD_CPU_TO_DDR:
+	{
+		u32 opt = (readl(sar) >> SAR_KIRKWOOD_DDR_RATIO) &
+			SAR_KIRKWOOD_DDR_RATIO_MASK;
+		*mult = kirkwood_cpu_ddr_ratios[opt][0];
+		*div = kirkwood_cpu_ddr_ratios[opt][1];
+		break;
+	}
+	}
+}
+
+static const struct core_clocks kirkwood_core_clocks = {
+	.get_tclk_freq = kirkwood_get_tclk_freq,
+	.get_cpu_freq = kirkwood_get_cpu_freq,
+	.get_clk_ratio = kirkwood_get_clk_ratio,
+	.ratios = kirkwood_core_ratios,
+	.num_ratios = ARRAY_SIZE(kirkwood_core_ratios),
+};
+
+static const u32 __initconst mv88f6180_cpu_frequencies[] = {
+	0, 0, 0, 0, 0,
+	600000000,
+	800000000,
+	1000000000
+};
+
+static u32 __init mv88f6180_get_cpu_freq(void __iomem *sar)
+{
+	u32 opt = (readl(sar) >> SAR_MV88F6180_CLK) & SAR_MV88F6180_CLK_MASK;
+	return mv88f6180_cpu_frequencies[opt];
+}
+
+static const int __initconst mv88f6180_cpu_ddr_ratios[8][2] = {
+	{ 0, 1 }, { 0, 1 }, { 0, 1 }, { 0, 1 },
+	{ 0, 1 }, { 1, 3 }, { 1, 4 }, { 1, 5 }
+};
+
+static void __init mv88f6180_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	switch (id) {
+	case KIRKWOOD_CPU_TO_L2:
+	{
+		/* mv88f6180 has a fixed 1:2 CPU-to-L2 ratio */
+		*mult = 1;
+		*div = 2;
+		break;
+	}
+	case KIRKWOOD_CPU_TO_DDR:
+	{
+		u32 opt = (readl(sar) >> SAR_MV88F6180_CLK) &
+			SAR_MV88F6180_CLK_MASK;
+		*mult = mv88f6180_cpu_ddr_ratios[opt][0];
+		*div = mv88f6180_cpu_ddr_ratios[opt][1];
+		break;
+	}
+	}
+}
+
+static const struct core_clocks mv88f6180_core_clocks = {
+	.get_tclk_freq = kirkwood_get_tclk_freq,
+	.get_cpu_freq = mv88f6180_get_cpu_freq,
+	.get_clk_ratio = mv88f6180_get_clk_ratio,
+	.ratios = kirkwood_core_ratios,
+	.num_ratios = ARRAY_SIZE(kirkwood_core_ratios),
+};
+#endif /* CONFIG_ARCH_KIRKWOOD */
+
+static const __initdata struct of_device_id clk_core_match[] = {
+#ifdef CONFIG_MACH_ARMADA_370_XP
+	{
+		.compatible = "marvell,armada-370-core-clock",
+		.data = &armada_370_core_clocks,
+	},
+	{
+		.compatible = "marvell,armada-xp-core-clock",
+		.data = &armada_xp_core_clocks,
+	},
+#endif
+#ifdef CONFIG_ARCH_DOVE
+	{
+		.compatible = "marvell,dove-core-clock",
+		.data = &dove_core_clocks,
+	},
+#endif
+
+#ifdef CONFIG_ARCH_KIRKWOOD
+	{
+		.compatible = "marvell,kirkwood-core-clock",
+		.data = &kirkwood_core_clocks,
+	},
+	{
+		.compatible = "marvell,mv88f6180-core-clock",
+		.data = &mv88f6180_core_clocks,
+	},
+#endif
+
+	{ }
+};
+
+void __init mvebu_core_clk_init(void)
+{
+	struct device_node *np;
+
+	for_each_matching_node(np, clk_core_match) {
+		const struct of_device_id *match =
+			of_match_node(clk_core_match, np);
+		mvebu_clk_core_setup(np, (struct core_clocks *)match->data);
+	}
+}
diff --git a/drivers/clk/mvebu/clk-core.h b/drivers/clk/mvebu/clk-core.h
new file mode 100644
index 0000000..28b5e02
--- /dev/null
+++ b/drivers/clk/mvebu/clk-core.h
@@ -0,0 +1,18 @@
+/*
+ *  * Marvell EBU clock core handling defined at reset
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MVEBU_CLK_CORE_H
+#define __MVEBU_CLK_CORE_H
+
+void __init mvebu_core_clk_init(void);
+
+#endif
diff --git a/drivers/clk/mvebu/clk-cpu.c b/drivers/clk/mvebu/clk-cpu.c
new file mode 100644
index 0000000..ff004578
--- /dev/null
+++ b/drivers/clk/mvebu/clk-cpu.c
@@ -0,0 +1,186 @@
+/*
+ * Marvell MVEBU CPU clock handling.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/delay.h>
+#include "clk-cpu.h"
+
+#define SYS_CTRL_CLK_DIVIDER_CTRL_OFFSET    0x0
+#define SYS_CTRL_CLK_DIVIDER_VALUE_OFFSET   0xC
+#define SYS_CTRL_CLK_DIVIDER_MASK	    0x3F
+
+#define MAX_CPU	    4
+struct cpu_clk {
+	struct clk_hw hw;
+	int cpu;
+	const char *clk_name;
+	const char *parent_name;
+	void __iomem *reg_base;
+};
+
+static struct clk **clks;
+
+static struct clk_onecell_data clk_data;
+
+#define to_cpu_clk(p) container_of(p, struct cpu_clk, hw)
+
+static unsigned long clk_cpu_recalc_rate(struct clk_hw *hwclk,
+					 unsigned long parent_rate)
+{
+	struct cpu_clk *cpuclk = to_cpu_clk(hwclk);
+	u32 reg, div;
+
+	reg = readl(cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_VALUE_OFFSET);
+	div = (reg >> (cpuclk->cpu * 8)) & SYS_CTRL_CLK_DIVIDER_MASK;
+	return parent_rate / div;
+}
+
+static long clk_cpu_round_rate(struct clk_hw *hwclk, unsigned long rate,
+			       unsigned long *parent_rate)
+{
+	/* Valid ratio are 1:1, 1:2 and 1:3 */
+	u32 div;
+
+	div = *parent_rate / rate;
+	if (div == 0)
+		div = 1;
+	else if (div > 3)
+		div = 3;
+
+	return *parent_rate / div;
+}
+
+static int clk_cpu_set_rate(struct clk_hw *hwclk, unsigned long rate,
+			    unsigned long parent_rate)
+{
+	struct cpu_clk *cpuclk = to_cpu_clk(hwclk);
+	u32 reg, div;
+	u32 reload_mask;
+
+	div = parent_rate / rate;
+	reg = (readl(cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_VALUE_OFFSET)
+		& (~(SYS_CTRL_CLK_DIVIDER_MASK << (cpuclk->cpu * 8))))
+		| (div << (cpuclk->cpu * 8));
+	writel(reg, cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_VALUE_OFFSET);
+	/* Set clock divider reload smooth bit mask */
+	reload_mask = 1 << (20 + cpuclk->cpu);
+
+	reg = readl(cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_CTRL_OFFSET)
+	    | reload_mask;
+	writel(reg, cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_CTRL_OFFSET);
+
+	/* Now trigger the clock update */
+	reg = readl(cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_CTRL_OFFSET)
+	    | 1 << 24;
+	writel(reg, cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_CTRL_OFFSET);
+
+	/* Wait for clocks to settle down then clear reload request */
+	udelay(1000);
+	reg &= ~(reload_mask | 1 << 24);
+	writel(reg, cpuclk->reg_base + SYS_CTRL_CLK_DIVIDER_CTRL_OFFSET);
+	udelay(1000);
+
+	return 0;
+}
+
+static const struct clk_ops cpu_ops = {
+	.recalc_rate = clk_cpu_recalc_rate,
+	.round_rate = clk_cpu_round_rate,
+	.set_rate = clk_cpu_set_rate,
+};
+
+void __init of_cpu_clk_setup(struct device_node *node)
+{
+	struct cpu_clk *cpuclk;
+	void __iomem *clock_complex_base = of_iomap(node, 0);
+	int ncpus = 0;
+	struct device_node *dn;
+
+	if (clock_complex_base == NULL) {
+		pr_err("%s: clock-complex base register not set\n",
+			__func__);
+		return;
+	}
+
+	for_each_node_by_type(dn, "cpu")
+		ncpus++;
+
+	cpuclk = kzalloc(ncpus * sizeof(*cpuclk), GFP_KERNEL);
+	if (WARN_ON(!cpuclk))
+		return;
+
+	clks = kzalloc(ncpus * sizeof(*clks), GFP_KERNEL);
+	if (WARN_ON(!clks))
+		return;
+
+	for_each_node_by_type(dn, "cpu") {
+		struct clk_init_data init;
+		struct clk *clk;
+		struct clk *parent_clk;
+		char *clk_name = kzalloc(5, GFP_KERNEL);
+		int cpu, err;
+
+		if (WARN_ON(!clk_name))
+			return;
+
+		err = of_property_read_u32(dn, "reg", &cpu);
+		if (WARN_ON(err))
+			return;
+
+		sprintf(clk_name, "cpu%d", cpu);
+		parent_clk = of_clk_get(node, 0);
+
+		cpuclk[cpu].parent_name = __clk_get_name(parent_clk);
+		cpuclk[cpu].clk_name = clk_name;
+		cpuclk[cpu].cpu = cpu;
+		cpuclk[cpu].reg_base = clock_complex_base;
+		cpuclk[cpu].hw.init = &init;
+
+		init.name = cpuclk[cpu].clk_name;
+		init.ops = &cpu_ops;
+		init.flags = 0;
+		init.parent_names = &cpuclk[cpu].parent_name;
+		init.num_parents = 1;
+
+		clk = clk_register(NULL, &cpuclk[cpu].hw);
+		if (WARN_ON(IS_ERR(clk)))
+			goto bail_out;
+		clks[cpu] = clk;
+	}
+	clk_data.clk_num = MAX_CPU;
+	clk_data.clks = clks;
+	of_clk_add_provider(node, of_clk_src_onecell_get, &clk_data);
+
+	return;
+bail_out:
+	kfree(clks);
+	kfree(cpuclk);
+}
+
+static const __initconst struct of_device_id clk_cpu_match[] = {
+	{
+		.compatible = "marvell,armada-xp-cpu-clock",
+		.data = of_cpu_clk_setup,
+	},
+	{
+		/* sentinel */
+	},
+};
+
+void __init mvebu_cpu_clk_init(void)
+{
+	of_clk_init(clk_cpu_match);
+}
diff --git a/drivers/clk/mvebu/clk-cpu.h b/drivers/clk/mvebu/clk-cpu.h
new file mode 100644
index 0000000..08e2aff
--- /dev/null
+++ b/drivers/clk/mvebu/clk-cpu.h
@@ -0,0 +1,22 @@
+/*
+ * Marvell MVEBU CPU clock handling.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MVEBU_CLK_CPU_H
+#define __MVEBU_CLK_CPU_H
+
+#ifdef CONFIG_MVEBU_CLK_CPU
+void __init mvebu_cpu_clk_init(void);
+#else
+static inline void mvebu_cpu_clk_init(void) {}
+#endif
+
+#endif
diff --git a/drivers/clk/mvebu/clk-gating-ctrl.c b/drivers/clk/mvebu/clk-gating-ctrl.c
new file mode 100644
index 0000000..c6d3c26
--- /dev/null
+++ b/drivers/clk/mvebu/clk-gating-ctrl.c
@@ -0,0 +1,249 @@
+/*
+ * Marvell MVEBU clock gating control.
+ *
+ * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
+ * Andrew Lunn <andrew@lunn.ch>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/clk/mvebu.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+struct mvebu_gating_ctrl {
+	spinlock_t lock;
+	struct clk **gates;
+	int num_gates;
+};
+
+struct mvebu_soc_descr {
+	const char *name;
+	const char *parent;
+	int bit_idx;
+};
+
+#define to_clk_gate(_hw) container_of(_hw, struct clk_gate, hw)
+
+static struct clk __init *mvebu_clk_gating_get_src(
+	struct of_phandle_args *clkspec, void *data)
+{
+	struct mvebu_gating_ctrl *ctrl = (struct mvebu_gating_ctrl *)data;
+	int n;
+
+	if (clkspec->args_count < 1)
+		return ERR_PTR(-EINVAL);
+
+	for (n = 0; n < ctrl->num_gates; n++) {
+		struct clk_gate *gate =
+			to_clk_gate(__clk_get_hw(ctrl->gates[n]));
+		if (clkspec->args[0] == gate->bit_idx)
+			return ctrl->gates[n];
+	}
+	return ERR_PTR(-ENODEV);
+}
+
+static void __init mvebu_clk_gating_setup(
+	struct device_node *np, const struct mvebu_soc_descr *descr)
+{
+	struct mvebu_gating_ctrl *ctrl;
+	struct clk *clk;
+	void __iomem *base;
+	const char *default_parent = NULL;
+	int n;
+
+	base = of_iomap(np, 0);
+
+	clk = of_clk_get(np, 0);
+	if (!IS_ERR(clk)) {
+		default_parent = __clk_get_name(clk);
+		clk_put(clk);
+	}
+
+	ctrl = kzalloc(sizeof(struct mvebu_gating_ctrl), GFP_KERNEL);
+	if (WARN_ON(!ctrl))
+		return;
+
+	spin_lock_init(&ctrl->lock);
+
+	/*
+	 * Count, allocate, and register clock gates
+	 */
+	for (n = 0; descr[n].name;)
+		n++;
+
+	ctrl->num_gates = n;
+	ctrl->gates = kzalloc(ctrl->num_gates * sizeof(struct clk *),
+			      GFP_KERNEL);
+	if (WARN_ON(!ctrl->gates)) {
+		kfree(ctrl);
+		return;
+	}
+
+	for (n = 0; n < ctrl->num_gates; n++) {
+		u8 flags = 0;
+		const char *parent =
+			(descr[n].parent) ? descr[n].parent : default_parent;
+
+		/*
+		 * On Armada 370, the DDR clock is a special case: it
+		 * isn't taken by any driver, but should anyway be
+		 * kept enabled, so we mark it as IGNORE_UNUSED for
+		 * now.
+		 */
+		if (!strcmp(descr[n].name, "ddr"))
+			flags |= CLK_IGNORE_UNUSED;
+
+		ctrl->gates[n] = clk_register_gate(NULL, descr[n].name, parent,
+				   flags, base, descr[n].bit_idx, 0, &ctrl->lock);
+		WARN_ON(IS_ERR(ctrl->gates[n]));
+	}
+	of_clk_add_provider(np, mvebu_clk_gating_get_src, ctrl);
+}
+
+/*
+ * SoC specific clock gating control
+ */
+
+#ifdef CONFIG_MACH_ARMADA_370
+static const struct mvebu_soc_descr __initconst armada_370_gating_descr[] = {
+	{ "audio", NULL, 0 },
+	{ "pex0_en", NULL, 1 },
+	{ "pex1_en", NULL,  2 },
+	{ "ge1", NULL, 3 },
+	{ "ge0", NULL, 4 },
+	{ "pex0", NULL, 5 },
+	{ "pex1", NULL, 9 },
+	{ "sata0", NULL, 15 },
+	{ "sdio", NULL, 17 },
+	{ "tdm", NULL, 25 },
+	{ "ddr", NULL, 28 },
+	{ "sata1", NULL, 30 },
+	{ }
+};
+#endif
+
+#ifdef CONFIG_MACH_ARMADA_XP
+static const struct mvebu_soc_descr __initconst armada_xp_gating_descr[] = {
+	{ "audio", NULL, 0 },
+	{ "ge3", NULL, 1 },
+	{ "ge2", NULL,  2 },
+	{ "ge1", NULL, 3 },
+	{ "ge0", NULL, 4 },
+	{ "pex0", NULL, 5 },
+	{ "pex1", NULL, 6 },
+	{ "pex2", NULL, 7 },
+	{ "pex3", NULL, 8 },
+	{ "bp", NULL, 13 },
+	{ "sata0lnk", NULL, 14 },
+	{ "sata0", "sata0lnk", 15 },
+	{ "lcd", NULL, 16 },
+	{ "sdio", NULL, 17 },
+	{ "usb0", NULL, 18 },
+	{ "usb1", NULL, 19 },
+	{ "usb2", NULL, 20 },
+	{ "xor0", NULL, 22 },
+	{ "crypto", NULL, 23 },
+	{ "tdm", NULL, 25 },
+	{ "xor1", NULL, 28 },
+	{ "sata1lnk", NULL, 29 },
+	{ "sata1", "sata1lnk", 30 },
+	{ }
+};
+#endif
+
+#ifdef CONFIG_ARCH_DOVE
+static const struct mvebu_soc_descr __initconst dove_gating_descr[] = {
+	{ "usb0", NULL, 0 },
+	{ "usb1", NULL, 1 },
+	{ "ge", "gephy", 2 },
+	{ "sata", NULL, 3 },
+	{ "pex0", NULL, 4 },
+	{ "pex1", NULL, 5 },
+	{ "sdio0", NULL, 8 },
+	{ "sdio1", NULL, 9 },
+	{ "nand", NULL, 10 },
+	{ "camera", NULL, 11 },
+	{ "i2s0", NULL, 12 },
+	{ "i2s1", NULL, 13 },
+	{ "crypto", NULL, 15 },
+	{ "ac97", NULL, 21 },
+	{ "pdma", NULL, 22 },
+	{ "xor0", NULL, 23 },
+	{ "xor1", NULL, 24 },
+	{ "gephy", NULL, 30 },
+	{ }
+};
+#endif
+
+#ifdef CONFIG_ARCH_KIRKWOOD
+static const struct mvebu_soc_descr __initconst kirkwood_gating_descr[] = {
+	{ "ge0", NULL, 0 },
+	{ "pex0", NULL, 2 },
+	{ "usb0", NULL, 3 },
+	{ "sdio", NULL, 4 },
+	{ "tsu", NULL, 5 },
+	{ "runit", NULL, 7 },
+	{ "xor0", NULL, 8 },
+	{ "audio", NULL, 9 },
+	{ "sata0", NULL, 14 },
+	{ "sata1", NULL, 15 },
+	{ "xor1", NULL, 16 },
+	{ "crypto", NULL, 17 },
+	{ "pex1", NULL, 18 },
+	{ "ge1", NULL, 19 },
+	{ "tdm", NULL, 20 },
+	{ }
+};
+#endif
+
+static const __initdata struct of_device_id clk_gating_match[] = {
+#ifdef CONFIG_MACH_ARMADA_370
+	{
+		.compatible = "marvell,armada-370-gating-clock",
+		.data = armada_370_gating_descr,
+	},
+#endif
+
+#ifdef CONFIG_MACH_ARMADA_XP
+	{
+		.compatible = "marvell,armada-xp-gating-clock",
+		.data = armada_xp_gating_descr,
+	},
+#endif
+
+#ifdef CONFIG_ARCH_DOVE
+	{
+		.compatible = "marvell,dove-gating-clock",
+		.data = dove_gating_descr,
+	},
+#endif
+
+#ifdef CONFIG_ARCH_KIRKWOOD
+	{
+		.compatible = "marvell,kirkwood-gating-clock",
+		.data = kirkwood_gating_descr,
+	},
+#endif
+
+	{ }
+};
+
+void __init mvebu_gating_clk_init(void)
+{
+	struct device_node *np;
+
+	for_each_matching_node(np, clk_gating_match) {
+		const struct of_device_id *match =
+			of_match_node(clk_gating_match, np);
+		mvebu_clk_gating_setup(np,
+		       (const struct mvebu_soc_descr *)match->data);
+	}
+}
diff --git a/drivers/clk/mvebu/clk-gating-ctrl.h b/drivers/clk/mvebu/clk-gating-ctrl.h
new file mode 100644
index 0000000..9275d1e
--- /dev/null
+++ b/drivers/clk/mvebu/clk-gating-ctrl.h
@@ -0,0 +1,22 @@
+/*
+ * Marvell EBU gating clock handling
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MVEBU_CLK_GATING_H
+#define __MVEBU_CLK_GATING_H
+
+#ifdef CONFIG_MVEBU_CLK_GATING
+void __init mvebu_gating_clk_init(void);
+#else
+void mvebu_gating_clk_init(void) {}
+#endif
+
+#endif
diff --git a/drivers/clk/mvebu/clk.c b/drivers/clk/mvebu/clk.c
new file mode 100644
index 0000000..855681b
--- /dev/null
+++ b/drivers/clk/mvebu/clk.c
@@ -0,0 +1,27 @@
+/*
+ * Marvell EBU SoC clock handling.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+#include <linux/clk/mvebu.h>
+#include <linux/of.h>
+#include "clk-core.h"
+#include "clk-cpu.h"
+#include "clk-gating-ctrl.h"
+
+void __init mvebu_clocks_init(void)
+{
+	mvebu_core_clk_init();
+	mvebu_gating_clk_init();
+	mvebu_cpu_clk_init();
+}
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 4674f94..a4605fd 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/kernel.h>
+#include <linux/clk.h>
 #include <linux/timer.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
@@ -167,7 +168,6 @@ void __init armada_370_xp_timer_init(void)
 	u32 u;
 	struct device_node *np;
 	unsigned int timer_clk;
-	int ret;
 	np = of_find_compatible_node(NULL, NULL, "marvell,armada-370-xp-timer");
 	timer_base = of_iomap(np, 0);
 	WARN_ON(!timer_base);
@@ -179,13 +179,14 @@ void __init armada_370_xp_timer_init(void)
 		       timer_base + TIMER_CTRL_OFF);
 		timer_clk = 25000000;
 	} else {
-		u32 clk = 0;
-		ret = of_property_read_u32(np, "clock-frequency", &clk);
-		WARN_ON(!clk || ret < 0);
+		unsigned long rate = 0;
+		struct clk *clk = of_clk_get(np, 0);
+		WARN_ON(IS_ERR(clk));
+		rate =  clk_get_rate(clk);
 		u = readl(timer_base + TIMER_CTRL_OFF);
 		writel(u & ~(TIMER0_25MHZ | TIMER1_25MHZ),
 		       timer_base + TIMER_CTRL_OFF);
-		timer_clk = clk / TIMER_DIVIDER;
+		timer_clk = rate / TIMER_DIVIDER;
 	}
 
 	/* We use timer 0 as clocksource, and timer 1 for
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index d12ad00..ac71f55 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -26,6 +26,9 @@
 #include <linux/platform_device.h>
 #include <linux/memory.h>
 #include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/irqdomain.h>
 #include <linux/platform_data/dma-mv_xor.h>
 
 #include "dmaengine.h"
@@ -34,14 +37,14 @@
 static void mv_xor_issue_pending(struct dma_chan *chan);
 
 #define to_mv_xor_chan(chan)		\
-	container_of(chan, struct mv_xor_chan, common)
-
-#define to_mv_xor_device(dev)		\
-	container_of(dev, struct mv_xor_device, common)
+	container_of(chan, struct mv_xor_chan, dmachan)
 
 #define to_mv_xor_slot(tx)		\
 	container_of(tx, struct mv_xor_desc_slot, async_tx)
 
+#define mv_chan_to_devp(chan)           \
+	((chan)->dmadev.dev)
+
 static void mv_desc_init(struct mv_xor_desc_slot *desc, unsigned long flags)
 {
 	struct mv_xor_desc *hw_desc = desc->hw_desc;
@@ -166,7 +169,7 @@ static int mv_is_err_intr(u32 intr_cause)
 static void mv_xor_device_clear_eoc_cause(struct mv_xor_chan *chan)
 {
 	u32 val = ~(1 << (chan->idx * 16));
-	dev_dbg(chan->device->common.dev, "%s, val 0x%08x\n", __func__, val);
+	dev_dbg(mv_chan_to_devp(chan), "%s, val 0x%08x\n", __func__, val);
 	__raw_writel(val, XOR_INTR_CAUSE(chan));
 }
 
@@ -206,9 +209,9 @@ static void mv_set_mode(struct mv_xor_chan *chan,
 		op_mode = XOR_OPERATION_MODE_MEMSET;
 		break;
 	default:
-		dev_printk(KERN_ERR, chan->device->common.dev,
-			   "error: unsupported operation %d.\n",
-			   type);
+		dev_err(mv_chan_to_devp(chan),
+			"error: unsupported operation %d.\n",
+			type);
 		BUG();
 		return;
 	}
@@ -223,7 +226,7 @@ static void mv_chan_activate(struct mv_xor_chan *chan)
 {
 	u32 activation;
 
-	dev_dbg(chan->device->common.dev, " activate chan.\n");
+	dev_dbg(mv_chan_to_devp(chan), " activate chan.\n");
 	activation = __raw_readl(XOR_ACTIVATION(chan));
 	activation |= 0x1;
 	__raw_writel(activation, XOR_ACTIVATION(chan));
@@ -251,7 +254,7 @@ static int mv_chan_xor_slot_count(size_t len, int src_cnt)
 static void mv_xor_free_slots(struct mv_xor_chan *mv_chan,
 			      struct mv_xor_desc_slot *slot)
 {
-	dev_dbg(mv_chan->device->common.dev, "%s %d slot %p\n",
+	dev_dbg(mv_chan_to_devp(mv_chan), "%s %d slot %p\n",
 		__func__, __LINE__, slot);
 
 	slot->slots_per_op = 0;
@@ -266,7 +269,7 @@ static void mv_xor_free_slots(struct mv_xor_chan *mv_chan,
 static void mv_xor_start_new_chain(struct mv_xor_chan *mv_chan,
 				   struct mv_xor_desc_slot *sw_desc)
 {
-	dev_dbg(mv_chan->device->common.dev, "%s %d: sw_desc %p\n",
+	dev_dbg(mv_chan_to_devp(mv_chan), "%s %d: sw_desc %p\n",
 		__func__, __LINE__, sw_desc);
 	if (sw_desc->type != mv_chan->current_type)
 		mv_set_mode(mv_chan, sw_desc->type);
@@ -284,7 +287,7 @@ static void mv_xor_start_new_chain(struct mv_xor_chan *mv_chan,
 		mv_chan_set_next_descriptor(mv_chan, sw_desc->async_tx.phys);
 	}
 	mv_chan->pending += sw_desc->slot_cnt;
-	mv_xor_issue_pending(&mv_chan->common);
+	mv_xor_issue_pending(&mv_chan->dmachan);
 }
 
 static dma_cookie_t
@@ -308,8 +311,7 @@ mv_xor_run_tx_complete_actions(struct mv_xor_desc_slot *desc,
 		 */
 		if (desc->group_head && desc->unmap_len) {
 			struct mv_xor_desc_slot *unmap = desc->group_head;
-			struct device *dev =
-				&mv_chan->device->pdev->dev;
+			struct device *dev = mv_chan_to_devp(mv_chan);
 			u32 len = unmap->unmap_len;
 			enum dma_ctrl_flags flags = desc->async_tx.flags;
 			u32 src_cnt;
@@ -353,7 +355,7 @@ mv_xor_clean_completed_slots(struct mv_xor_chan *mv_chan)
 {
 	struct mv_xor_desc_slot *iter, *_iter;
 
-	dev_dbg(mv_chan->device->common.dev, "%s %d\n", __func__, __LINE__);
+	dev_dbg(mv_chan_to_devp(mv_chan), "%s %d\n", __func__, __LINE__);
 	list_for_each_entry_safe(iter, _iter, &mv_chan->completed_slots,
 				 completed_node) {
 
@@ -369,7 +371,7 @@ static int
 mv_xor_clean_slot(struct mv_xor_desc_slot *desc,
 	struct mv_xor_chan *mv_chan)
 {
-	dev_dbg(mv_chan->device->common.dev, "%s %d: desc %p flags %d\n",
+	dev_dbg(mv_chan_to_devp(mv_chan), "%s %d: desc %p flags %d\n",
 		__func__, __LINE__, desc, desc->async_tx.flags);
 	list_del(&desc->chain_node);
 	/* the client is allowed to attach dependent operations
@@ -393,8 +395,8 @@ static void __mv_xor_slot_cleanup(struct mv_xor_chan *mv_chan)
 	u32 current_desc = mv_chan_get_current_desc(mv_chan);
 	int seen_current = 0;
 
-	dev_dbg(mv_chan->device->common.dev, "%s %d\n", __func__, __LINE__);
-	dev_dbg(mv_chan->device->common.dev, "current_desc %x\n", current_desc);
+	dev_dbg(mv_chan_to_devp(mv_chan), "%s %d\n", __func__, __LINE__);
+	dev_dbg(mv_chan_to_devp(mv_chan), "current_desc %x\n", current_desc);
 	mv_xor_clean_completed_slots(mv_chan);
 
 	/* free completed slots from the chain starting with
@@ -438,7 +440,7 @@ static void __mv_xor_slot_cleanup(struct mv_xor_chan *mv_chan)
 	}
 
 	if (cookie > 0)
-		mv_chan->common.completed_cookie = cookie;
+		mv_chan->dmachan.completed_cookie = cookie;
 }
 
 static void
@@ -547,7 +549,7 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
 	dma_cookie_t cookie;
 	int new_hw_chain = 1;
 
-	dev_dbg(mv_chan->device->common.dev,
+	dev_dbg(mv_chan_to_devp(mv_chan),
 		"%s sw_desc %p: async_tx %p\n",
 		__func__, sw_desc, &sw_desc->async_tx);
 
@@ -570,7 +572,7 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
 		if (!mv_can_chain(grp_start))
 			goto submit_done;
 
-		dev_dbg(mv_chan->device->common.dev, "Append to last desc %x\n",
+		dev_dbg(mv_chan_to_devp(mv_chan), "Append to last desc %x\n",
 			old_chain_tail->async_tx.phys);
 
 		/* fix up the hardware chain */
@@ -604,9 +606,7 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 	int idx;
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
 	struct mv_xor_desc_slot *slot = NULL;
-	struct mv_xor_platform_data *plat_data =
-		mv_chan->device->pdev->dev.platform_data;
-	int num_descs_in_pool = plat_data->pool_size/MV_XOR_SLOT_SIZE;
+	int num_descs_in_pool = MV_XOR_POOL_SIZE/MV_XOR_SLOT_SIZE;
 
 	/* Allocate descriptor slots */
 	idx = mv_chan->slots_allocated;
@@ -617,7 +617,7 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 				" %d descriptor slots", idx);
 			break;
 		}
-		hw_desc = (char *) mv_chan->device->dma_desc_pool_virt;
+		hw_desc = (char *) mv_chan->dma_desc_pool_virt;
 		slot->hw_desc = (void *) &hw_desc[idx * MV_XOR_SLOT_SIZE];
 
 		dma_async_tx_descriptor_init(&slot->async_tx, chan);
@@ -625,7 +625,7 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
 		INIT_LIST_HEAD(&slot->tx_list);
-		hw_desc = (char *) mv_chan->device->dma_desc_pool;
+		hw_desc = (char *) mv_chan->dma_desc_pool;
 		slot->async_tx.phys =
 			(dma_addr_t) &hw_desc[idx * MV_XOR_SLOT_SIZE];
 		slot->idx = idx++;
@@ -641,7 +641,7 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 					struct mv_xor_desc_slot,
 					slot_node);
 
-	dev_dbg(mv_chan->device->common.dev,
+	dev_dbg(mv_chan_to_devp(mv_chan),
 		"allocated %d descriptor slots last_used: %p\n",
 		mv_chan->slots_allocated, mv_chan->last_used);
 
@@ -656,7 +656,7 @@ mv_xor_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	struct mv_xor_desc_slot *sw_desc, *grp_start;
 	int slot_cnt;
 
-	dev_dbg(mv_chan->device->common.dev,
+	dev_dbg(mv_chan_to_devp(mv_chan),
 		"%s dest: %x src %x len: %u flags: %ld\n",
 		__func__, dest, src, len, flags);
 	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
@@ -680,7 +680,7 @@ mv_xor_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	}
 	spin_unlock_bh(&mv_chan->lock);
 
-	dev_dbg(mv_chan->device->common.dev,
+	dev_dbg(mv_chan_to_devp(mv_chan),
 		"%s sw_desc %p async_tx %p\n",
 		__func__, sw_desc, sw_desc ? &sw_desc->async_tx : 0);
 
@@ -695,7 +695,7 @@ mv_xor_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
 	struct mv_xor_desc_slot *sw_desc, *grp_start;
 	int slot_cnt;
 
-	dev_dbg(mv_chan->device->common.dev,
+	dev_dbg(mv_chan_to_devp(mv_chan),
 		"%s dest: %x len: %u flags: %ld\n",
 		__func__, dest, len, flags);
 	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
@@ -718,7 +718,7 @@ mv_xor_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
 		sw_desc->unmap_len = len;
 	}
 	spin_unlock_bh(&mv_chan->lock);
-	dev_dbg(mv_chan->device->common.dev,
+	dev_dbg(mv_chan_to_devp(mv_chan),
 		"%s sw_desc %p async_tx %p \n",
 		__func__, sw_desc, &sw_desc->async_tx);
 	return sw_desc ? &sw_desc->async_tx : NULL;
@@ -737,7 +737,7 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 
 	BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
-	dev_dbg(mv_chan->device->common.dev,
+	dev_dbg(mv_chan_to_devp(mv_chan),
 		"%s src_cnt: %d len: dest %x %u flags: %ld\n",
 		__func__, src_cnt, len, dest, flags);
 
@@ -758,7 +758,7 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 			mv_desc_set_src_addr(grp_start, src_cnt, src[src_cnt]);
 	}
 	spin_unlock_bh(&mv_chan->lock);
-	dev_dbg(mv_chan->device->common.dev,
+	dev_dbg(mv_chan_to_devp(mv_chan),
 		"%s sw_desc %p async_tx %p \n",
 		__func__, sw_desc, &sw_desc->async_tx);
 	return sw_desc ? &sw_desc->async_tx : NULL;
@@ -791,12 +791,12 @@ static void mv_xor_free_chan_resources(struct dma_chan *chan)
 	}
 	mv_chan->last_used = NULL;
 
-	dev_dbg(mv_chan->device->common.dev, "%s slots_allocated %d\n",
+	dev_dbg(mv_chan_to_devp(mv_chan), "%s slots_allocated %d\n",
 		__func__, mv_chan->slots_allocated);
 	spin_unlock_bh(&mv_chan->lock);
 
 	if (in_use_descs)
-		dev_err(mv_chan->device->common.dev,
+		dev_err(mv_chan_to_devp(mv_chan),
 			"freeing %d in use descriptors!\n", in_use_descs);
 }
 
@@ -828,42 +828,42 @@ static void mv_dump_xor_regs(struct mv_xor_chan *chan)
 	u32 val;
 
 	val = __raw_readl(XOR_CONFIG(chan));
-	dev_printk(KERN_ERR, chan->device->common.dev,
-		   "config       0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan),
+		"config       0x%08x.\n", val);
 
 	val = __raw_readl(XOR_ACTIVATION(chan));
-	dev_printk(KERN_ERR, chan->device->common.dev,
-		   "activation   0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan),
+		"activation   0x%08x.\n", val);
 
 	val = __raw_readl(XOR_INTR_CAUSE(chan));
-	dev_printk(KERN_ERR, chan->device->common.dev,
-		   "intr cause   0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan),
+		"intr cause   0x%08x.\n", val);
 
 	val = __raw_readl(XOR_INTR_MASK(chan));
-	dev_printk(KERN_ERR, chan->device->common.dev,
-		   "intr mask    0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan),
+		"intr mask    0x%08x.\n", val);
 
 	val = __raw_readl(XOR_ERROR_CAUSE(chan));
-	dev_printk(KERN_ERR, chan->device->common.dev,
-		   "error cause  0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan),
+		"error cause  0x%08x.\n", val);
 
 	val = __raw_readl(XOR_ERROR_ADDR(chan));
-	dev_printk(KERN_ERR, chan->device->common.dev,
-		   "error addr   0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan),
+		"error addr   0x%08x.\n", val);
 }
 
 static void mv_xor_err_interrupt_handler(struct mv_xor_chan *chan,
 					 u32 intr_cause)
 {
 	if (intr_cause & (1 << 4)) {
-	     dev_dbg(chan->device->common.dev,
+	     dev_dbg(mv_chan_to_devp(chan),
 		     "ignore this error\n");
 	     return;
 	}
 
-	dev_printk(KERN_ERR, chan->device->common.dev,
-		   "error on chan %d. intr cause 0x%08x.\n",
-		   chan->idx, intr_cause);
+	dev_err(mv_chan_to_devp(chan),
+		"error on chan %d. intr cause 0x%08x.\n",
+		chan->idx, intr_cause);
 
 	mv_dump_xor_regs(chan);
 	BUG();
@@ -874,7 +874,7 @@ static irqreturn_t mv_xor_interrupt_handler(int irq, void *data)
 	struct mv_xor_chan *chan = data;
 	u32 intr_cause = mv_chan_get_intr_cause(chan);
 
-	dev_dbg(chan->device->common.dev, "intr cause %x\n", intr_cause);
+	dev_dbg(mv_chan_to_devp(chan), "intr cause %x\n", intr_cause);
 
 	if (mv_is_err_intr(intr_cause))
 		mv_xor_err_interrupt_handler(chan, intr_cause);
@@ -901,7 +901,7 @@ static void mv_xor_issue_pending(struct dma_chan *chan)
  */
 #define MV_XOR_TEST_SIZE 2000
 
-static int mv_xor_memcpy_self_test(struct mv_xor_device *device)
+static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan)
 {
 	int i;
 	void *src, *dest;
@@ -910,7 +910,6 @@ static int mv_xor_memcpy_self_test(struct mv_xor_device *device)
 	dma_cookie_t cookie;
 	struct dma_async_tx_descriptor *tx;
 	int err = 0;
-	struct mv_xor_chan *mv_chan;
 
 	src = kmalloc(sizeof(u8) * MV_XOR_TEST_SIZE, GFP_KERNEL);
 	if (!src)
@@ -926,10 +925,7 @@ static int mv_xor_memcpy_self_test(struct mv_xor_device *device)
 	for (i = 0; i < MV_XOR_TEST_SIZE; i++)
 		((u8 *) src)[i] = (u8)i;
 
-	/* Start copy, using first DMA channel */
-	dma_chan = container_of(device->common.channels.next,
-				struct dma_chan,
-				device_node);
+	dma_chan = &mv_chan->dmachan;
 	if (mv_xor_alloc_chan_resources(dma_chan) < 1) {
 		err = -ENODEV;
 		goto out;
@@ -950,18 +946,17 @@ static int mv_xor_memcpy_self_test(struct mv_xor_device *device)
 
 	if (mv_xor_status(dma_chan, cookie, NULL) !=
 	    DMA_SUCCESS) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
-			   "Self-test copy timed out, disabling\n");
+		dev_err(dma_chan->device->dev,
+			"Self-test copy timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
 	}
 
-	mv_chan = to_mv_xor_chan(dma_chan);
-	dma_sync_single_for_cpu(&mv_chan->device->pdev->dev, dest_dma,
+	dma_sync_single_for_cpu(dma_chan->device->dev, dest_dma,
 				MV_XOR_TEST_SIZE, DMA_FROM_DEVICE);
 	if (memcmp(src, dest, MV_XOR_TEST_SIZE)) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
-			   "Self-test copy failed compare, disabling\n");
+		dev_err(dma_chan->device->dev,
+			"Self-test copy failed compare, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
 	}
@@ -976,7 +971,7 @@ out:
 
 #define MV_XOR_NUM_SRC_TEST 4 /* must be <= 15 */
 static int
-mv_xor_xor_self_test(struct mv_xor_device *device)
+mv_xor_xor_self_test(struct mv_xor_chan *mv_chan)
 {
 	int i, src_idx;
 	struct page *dest;
@@ -989,7 +984,6 @@ mv_xor_xor_self_test(struct mv_xor_device *device)
 	u8 cmp_byte = 0;
 	u32 cmp_word;
 	int err = 0;
-	struct mv_xor_chan *mv_chan;
 
 	for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) {
 		xor_srcs[src_idx] = alloc_page(GFP_KERNEL);
@@ -1022,9 +1016,7 @@ mv_xor_xor_self_test(struct mv_xor_device *device)
 
 	memset(page_address(dest), 0, PAGE_SIZE);
 
-	dma_chan = container_of(device->common.channels.next,
-				struct dma_chan,
-				device_node);
+	dma_chan = &mv_chan->dmachan;
 	if (mv_xor_alloc_chan_resources(dma_chan) < 1) {
 		err = -ENODEV;
 		goto out;
@@ -1048,22 +1040,21 @@ mv_xor_xor_self_test(struct mv_xor_device *device)
 
 	if (mv_xor_status(dma_chan, cookie, NULL) !=
 	    DMA_SUCCESS) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
-			   "Self-test xor timed out, disabling\n");
+		dev_err(dma_chan->device->dev,
+			"Self-test xor timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
 	}
 
-	mv_chan = to_mv_xor_chan(dma_chan);
-	dma_sync_single_for_cpu(&mv_chan->device->pdev->dev, dest_dma,
+	dma_sync_single_for_cpu(dma_chan->device->dev, dest_dma,
 				PAGE_SIZE, DMA_FROM_DEVICE);
 	for (i = 0; i < (PAGE_SIZE / sizeof(u32)); i++) {
 		u32 *ptr = page_address(dest);
 		if (ptr[i] != cmp_word) {
-			dev_printk(KERN_ERR, dma_chan->device->dev,
-				   "Self-test xor failed compare, disabling."
-				   " index %d, data %x, expected %x\n", i,
-				   ptr[i], cmp_word);
+			dev_err(dma_chan->device->dev,
+				"Self-test xor failed compare, disabling."
+				" index %d, data %x, expected %x\n", i,
+				ptr[i], cmp_word);
 			err = -ENODEV;
 			goto free_resources;
 		}
@@ -1079,62 +1070,66 @@ out:
 	return err;
 }
 
-static int __devexit mv_xor_remove(struct platform_device *dev)
+/* This driver does not implement any of the optional DMA operations. */
+static int
+mv_xor_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+	       unsigned long arg)
+{
+	return -ENOSYS;
+}
+
+static int mv_xor_channel_remove(struct mv_xor_chan *mv_chan)
 {
-	struct mv_xor_device *device = platform_get_drvdata(dev);
 	struct dma_chan *chan, *_chan;
-	struct mv_xor_chan *mv_chan;
-	struct mv_xor_platform_data *plat_data = dev->dev.platform_data;
+	struct device *dev = mv_chan->dmadev.dev;
 
-	dma_async_device_unregister(&device->common);
+	dma_async_device_unregister(&mv_chan->dmadev);
 
-	dma_free_coherent(&dev->dev, plat_data->pool_size,
-			device->dma_desc_pool_virt, device->dma_desc_pool);
+	dma_free_coherent(dev, MV_XOR_POOL_SIZE,
+			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
 
-	list_for_each_entry_safe(chan, _chan, &device->common.channels,
-				device_node) {
-		mv_chan = to_mv_xor_chan(chan);
+	list_for_each_entry_safe(chan, _chan, &mv_chan->dmadev.channels,
+				 device_node) {
 		list_del(&chan->device_node);
 	}
 
+	free_irq(mv_chan->irq, mv_chan);
+
 	return 0;
 }
 
-static int mv_xor_probe(struct platform_device *pdev)
+static struct mv_xor_chan *
+mv_xor_channel_add(struct mv_xor_device *xordev,
+		   struct platform_device *pdev,
+		   int idx, dma_cap_mask_t cap_mask, int irq)
 {
 	int ret = 0;
-	int irq;
-	struct mv_xor_device *adev;
 	struct mv_xor_chan *mv_chan;
 	struct dma_device *dma_dev;
-	struct mv_xor_platform_data *plat_data = pdev->dev.platform_data;
 
+	mv_chan = devm_kzalloc(&pdev->dev, sizeof(*mv_chan), GFP_KERNEL);
+	if (!mv_chan) {
+		ret = -ENOMEM;
+		goto err_free_dma;
+	}
 
-	adev = devm_kzalloc(&pdev->dev, sizeof(*adev), GFP_KERNEL);
-	if (!adev)
-		return -ENOMEM;
+	mv_chan->idx = idx;
+	mv_chan->irq = irq;
 
-	dma_dev = &adev->common;
+	dma_dev = &mv_chan->dmadev;
 
 	/* allocate coherent memory for hardware descriptors
 	 * note: writecombine gives slightly better performance, but
 	 * requires that we explicitly flush the writes
 	 */
-	adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
-							  plat_data->pool_size,
-							  &adev->dma_desc_pool,
-							  GFP_KERNEL);
-	if (!adev->dma_desc_pool_virt)
-		return -ENOMEM;
-
-	adev->id = plat_data->hw_id;
+	mv_chan->dma_desc_pool_virt =
+	  dma_alloc_writecombine(&pdev->dev, MV_XOR_POOL_SIZE,
+				 &mv_chan->dma_desc_pool, GFP_KERNEL);
+	if (!mv_chan->dma_desc_pool_virt)
+		return ERR_PTR(-ENOMEM);
 
 	/* discover transaction capabilites from the platform data */
-	dma_dev->cap_mask = plat_data->cap_mask;
-	adev->pdev = pdev;
-	platform_set_drvdata(pdev, adev);
-
-	adev->shared = platform_get_drvdata(plat_data->shared);
+	dma_dev->cap_mask = cap_mask;
 
 	INIT_LIST_HEAD(&dma_dev->channels);
 
@@ -1143,6 +1138,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 	dma_dev->device_free_chan_resources = mv_xor_free_chan_resources;
 	dma_dev->device_tx_status = mv_xor_status;
 	dma_dev->device_issue_pending = mv_xor_issue_pending;
+	dma_dev->device_control = mv_xor_control;
 	dma_dev->dev = &pdev->dev;
 
 	/* set prep routines based on capability */
@@ -1155,15 +1151,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 		dma_dev->device_prep_dma_xor = mv_xor_prep_dma_xor;
 	}
 
-	mv_chan = devm_kzalloc(&pdev->dev, sizeof(*mv_chan), GFP_KERNEL);
-	if (!mv_chan) {
-		ret = -ENOMEM;
-		goto err_free_dma;
-	}
-	mv_chan->device = adev;
-	mv_chan->idx = plat_data->hw_id;
-	mv_chan->mmr_base = adev->shared->xor_base;
-
+	mv_chan->mmr_base = xordev->xor_base;
 	if (!mv_chan->mmr_base) {
 		ret = -ENOMEM;
 		goto err_free_dma;
@@ -1174,14 +1162,8 @@ static int mv_xor_probe(struct platform_device *pdev)
 	/* clear errors before enabling interrupts */
 	mv_xor_device_clear_err_status(mv_chan);
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		ret = irq;
-		goto err_free_dma;
-	}
-	ret = devm_request_irq(&pdev->dev, irq,
-			       mv_xor_interrupt_handler,
-			       0, dev_name(&pdev->dev), mv_chan);
+	ret = request_irq(mv_chan->irq, mv_xor_interrupt_handler,
+			  0, dev_name(&pdev->dev), mv_chan);
 	if (ret)
 		goto err_free_dma;
 
@@ -1193,26 +1175,26 @@ static int mv_xor_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&mv_chan->chain);
 	INIT_LIST_HEAD(&mv_chan->completed_slots);
 	INIT_LIST_HEAD(&mv_chan->all_slots);
-	mv_chan->common.device = dma_dev;
-	dma_cookie_init(&mv_chan->common);
+	mv_chan->dmachan.device = dma_dev;
+	dma_cookie_init(&mv_chan->dmachan);
 
-	list_add_tail(&mv_chan->common.device_node, &dma_dev->channels);
+	list_add_tail(&mv_chan->dmachan.device_node, &dma_dev->channels);
 
 	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) {
-		ret = mv_xor_memcpy_self_test(adev);
+		ret = mv_xor_memcpy_self_test(mv_chan);
 		dev_dbg(&pdev->dev, "memcpy self test returned %d\n", ret);
 		if (ret)
-			goto err_free_dma;
+			goto err_free_irq;
 	}
 
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) {
-		ret = mv_xor_xor_self_test(adev);
+		ret = mv_xor_xor_self_test(mv_chan);
 		dev_dbg(&pdev->dev, "xor self test returned %d\n", ret);
 		if (ret)
-			goto err_free_dma;
+			goto err_free_irq;
 	}
 
-	dev_printk(KERN_INFO, &pdev->dev, "Marvell XOR: "
+	dev_info(&pdev->dev, "Marvell XOR: "
 	  "( %s%s%s%s)\n",
 	  dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
 	  dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)  ? "fill " : "",
@@ -1220,20 +1202,21 @@ static int mv_xor_probe(struct platform_device *pdev)
 	  dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
 
 	dma_async_device_register(dma_dev);
-	goto out;
+	return mv_chan;
 
+err_free_irq:
+	free_irq(mv_chan->irq, mv_chan);
  err_free_dma:
-	dma_free_coherent(&adev->pdev->dev, plat_data->pool_size,
-			adev->dma_desc_pool_virt, adev->dma_desc_pool);
- out:
-	return ret;
+	dma_free_coherent(&pdev->dev, MV_XOR_POOL_SIZE,
+			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
+	return ERR_PTR(ret);
 }
 
 static void
-mv_xor_conf_mbus_windows(struct mv_xor_shared_private *msp,
+mv_xor_conf_mbus_windows(struct mv_xor_device *xordev,
 			 const struct mbus_dram_target_info *dram)
 {
-	void __iomem *base = msp->xor_base;
+	void __iomem *base = xordev->xor_base;
 	u32 win_enable = 0;
 	int i;
 
@@ -1258,99 +1241,176 @@ mv_xor_conf_mbus_windows(struct mv_xor_shared_private *msp,
 
 	writel(win_enable, base + WINDOW_BAR_ENABLE(0));
 	writel(win_enable, base + WINDOW_BAR_ENABLE(1));
+	writel(0, base + WINDOW_OVERRIDE_CTRL(0));
+	writel(0, base + WINDOW_OVERRIDE_CTRL(1));
 }
 
-static struct platform_driver mv_xor_driver = {
-	.probe		= mv_xor_probe,
-	.remove		= mv_xor_remove,
-	.driver		= {
-		.owner	= THIS_MODULE,
-		.name	= MV_XOR_NAME,
-	},
-};
-
-static int mv_xor_shared_probe(struct platform_device *pdev)
+static int mv_xor_probe(struct platform_device *pdev)
 {
 	const struct mbus_dram_target_info *dram;
-	struct mv_xor_shared_private *msp;
+	struct mv_xor_device *xordev;
+	struct mv_xor_platform_data *pdata = pdev->dev.platform_data;
 	struct resource *res;
+	int i, ret;
 
-	dev_printk(KERN_NOTICE, &pdev->dev, "Marvell shared XOR driver\n");
+	dev_notice(&pdev->dev, "Marvell XOR driver\n");
 
-	msp = devm_kzalloc(&pdev->dev, sizeof(*msp), GFP_KERNEL);
-	if (!msp)
+	xordev = devm_kzalloc(&pdev->dev, sizeof(*xordev), GFP_KERNEL);
+	if (!xordev)
 		return -ENOMEM;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -ENODEV;
 
-	msp->xor_base = devm_ioremap(&pdev->dev, res->start,
-				     resource_size(res));
-	if (!msp->xor_base)
+	xordev->xor_base = devm_ioremap(&pdev->dev, res->start,
+					resource_size(res));
+	if (!xordev->xor_base)
 		return -EBUSY;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	if (!res)
 		return -ENODEV;
 
-	msp->xor_high_base = devm_ioremap(&pdev->dev, res->start,
-					  resource_size(res));
-	if (!msp->xor_high_base)
+	xordev->xor_high_base = devm_ioremap(&pdev->dev, res->start,
+					     resource_size(res));
+	if (!xordev->xor_high_base)
 		return -EBUSY;
 
-	platform_set_drvdata(pdev, msp);
+	platform_set_drvdata(pdev, xordev);
 
 	/*
 	 * (Re-)program MBUS remapping windows if we are asked to.
 	 */
 	dram = mv_mbus_dram_info();
 	if (dram)
-		mv_xor_conf_mbus_windows(msp, dram);
+		mv_xor_conf_mbus_windows(xordev, dram);
 
 	/* Not all platforms can gate the clock, so it is not
 	 * an error if the clock does not exists.
 	 */
-	msp->clk = clk_get(&pdev->dev, NULL);
-	if (!IS_ERR(msp->clk))
-		clk_prepare_enable(msp->clk);
+	xordev->clk = clk_get(&pdev->dev, NULL);
+	if (!IS_ERR(xordev->clk))
+		clk_prepare_enable(xordev->clk);
+
+	if (pdev->dev.of_node) {
+		struct device_node *np;
+		int i = 0;
+
+		for_each_child_of_node(pdev->dev.of_node, np) {
+			dma_cap_mask_t cap_mask;
+			int irq;
+
+			dma_cap_zero(cap_mask);
+			if (of_property_read_bool(np, "dmacap,memcpy"))
+				dma_cap_set(DMA_MEMCPY, cap_mask);
+			if (of_property_read_bool(np, "dmacap,xor"))
+				dma_cap_set(DMA_XOR, cap_mask);
+			if (of_property_read_bool(np, "dmacap,memset"))
+				dma_cap_set(DMA_MEMSET, cap_mask);
+			if (of_property_read_bool(np, "dmacap,interrupt"))
+				dma_cap_set(DMA_INTERRUPT, cap_mask);
+
+			irq = irq_of_parse_and_map(np, 0);
+			if (!irq) {
+				ret = -ENODEV;
+				goto err_channel_add;
+			}
+
+			xordev->channels[i] =
+				mv_xor_channel_add(xordev, pdev, i,
+						   cap_mask, irq);
+			if (IS_ERR(xordev->channels[i])) {
+				ret = PTR_ERR(xordev->channels[i]);
+				xordev->channels[i] = NULL;
+				irq_dispose_mapping(irq);
+				goto err_channel_add;
+			}
+
+			i++;
+		}
+	} else if (pdata && pdata->channels) {
+		for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+			struct mv_xor_channel_data *cd;
+			int irq;
+
+			cd = &pdata->channels[i];
+			if (!cd) {
+				ret = -ENODEV;
+				goto err_channel_add;
+			}
+
+			irq = platform_get_irq(pdev, i);
+			if (irq < 0) {
+				ret = irq;
+				goto err_channel_add;
+			}
+
+			xordev->channels[i] =
+				mv_xor_channel_add(xordev, pdev, i,
+						   cd->cap_mask, irq);
+			if (IS_ERR(xordev->channels[i])) {
+				ret = PTR_ERR(xordev->channels[i]);
+				goto err_channel_add;
+			}
+		}
+	}
 
 	return 0;
+
+err_channel_add:
+	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++)
+		if (xordev->channels[i]) {
+			if (pdev->dev.of_node)
+				irq_dispose_mapping(xordev->channels[i]->irq);
+			mv_xor_channel_remove(xordev->channels[i]);
+		}
+
+	clk_disable_unprepare(xordev->clk);
+	clk_put(xordev->clk);
+	return ret;
 }
 
-static int mv_xor_shared_remove(struct platform_device *pdev)
+static int mv_xor_remove(struct platform_device *pdev)
 {
-	struct mv_xor_shared_private *msp = platform_get_drvdata(pdev);
+	struct mv_xor_device *xordev = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+		if (xordev->channels[i])
+			mv_xor_channel_remove(xordev->channels[i]);
+	}
 
-	if (!IS_ERR(msp->clk)) {
-		clk_disable_unprepare(msp->clk);
-		clk_put(msp->clk);
+	if (!IS_ERR(xordev->clk)) {
+		clk_disable_unprepare(xordev->clk);
+		clk_put(xordev->clk);
 	}
 
 	return 0;
 }
 
-static struct platform_driver mv_xor_shared_driver = {
-	.probe		= mv_xor_shared_probe,
-	.remove		= mv_xor_shared_remove,
+#ifdef CONFIG_OF
+static struct of_device_id mv_xor_dt_ids[] = {
+       { .compatible = "marvell,orion-xor", },
+       {},
+};
+MODULE_DEVICE_TABLE(of, mv_xor_dt_ids);
+#endif
+
+static struct platform_driver mv_xor_driver = {
+	.probe		= mv_xor_probe,
+	.remove		= mv_xor_remove,
 	.driver		= {
-		.owner	= THIS_MODULE,
-		.name	= MV_XOR_SHARED_NAME,
+		.owner	        = THIS_MODULE,
+		.name	        = MV_XOR_NAME,
+		.of_match_table = of_match_ptr(mv_xor_dt_ids),
 	},
 };
 
 
 static int __init mv_xor_init(void)
 {
-	int rc;
-
-	rc = platform_driver_register(&mv_xor_shared_driver);
-	if (!rc) {
-		rc = platform_driver_register(&mv_xor_driver);
-		if (rc)
-			platform_driver_unregister(&mv_xor_shared_driver);
-	}
-	return rc;
+	return platform_driver_register(&mv_xor_driver);
 }
 module_init(mv_xor_init);
 
@@ -1359,7 +1419,6 @@ module_init(mv_xor_init);
 static void __exit mv_xor_exit(void)
 {
 	platform_driver_unregister(&mv_xor_driver);
-	platform_driver_unregister(&mv_xor_shared_driver);
 	return;
 }
 
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index a5b422f..c632a47 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -24,8 +24,10 @@
 #include <linux/interrupt.h>
 
 #define USE_TIMER
+#define MV_XOR_POOL_SIZE		PAGE_SIZE
 #define MV_XOR_SLOT_SIZE		64
 #define MV_XOR_THRESHOLD		1
+#define MV_XOR_MAX_CHANNELS             2
 
 #define XOR_OPERATION_MODE_XOR		0
 #define XOR_OPERATION_MODE_MEMCPY	2
@@ -51,29 +53,13 @@
 #define WINDOW_SIZE(w)		(0x270 + ((w) << 2))
 #define WINDOW_REMAP_HIGH(w)	(0x290 + ((w) << 2))
 #define WINDOW_BAR_ENABLE(chan)	(0x240 + ((chan) << 2))
+#define WINDOW_OVERRIDE_CTRL(chan)	(0x2A0 + ((chan) << 2))
 
-struct mv_xor_shared_private {
-	void __iomem	*xor_base;
-	void __iomem	*xor_high_base;
-	struct clk	*clk;
-};
-
-
-/**
- * struct mv_xor_device - internal representation of a XOR device
- * @pdev: Platform device
- * @id: HW XOR Device selector
- * @dma_desc_pool: base of DMA descriptor region (DMA address)
- * @dma_desc_pool_virt: base of DMA descriptor region (CPU address)
- * @common: embedded struct dma_device
- */
 struct mv_xor_device {
-	struct platform_device		*pdev;
-	int				id;
-	dma_addr_t			dma_desc_pool;
-	void				*dma_desc_pool_virt;
-	struct dma_device		common;
-	struct mv_xor_shared_private	*shared;
+	void __iomem	     *xor_base;
+	void __iomem	     *xor_high_base;
+	struct clk	     *clk;
+	struct mv_xor_chan   *channels[MV_XOR_MAX_CHANNELS];
 };
 
 /**
@@ -96,11 +82,15 @@ struct mv_xor_chan {
 	spinlock_t		lock; /* protects the descriptor slot pool */
 	void __iomem		*mmr_base;
 	unsigned int		idx;
+	int                     irq;
 	enum dma_transaction_type	current_type;
 	struct list_head	chain;
 	struct list_head	completed_slots;
-	struct mv_xor_device	*device;
-	struct dma_chan		common;
+	dma_addr_t		dma_desc_pool;
+	void			*dma_desc_pool_virt;
+	size_t                  pool_size;
+	struct dma_device	dmadev;
+	struct dma_chan		dmachan;
 	struct mv_xor_desc_slot	*last_used;
 	struct list_head	all_slots;
 	int			slots_allocated;
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 0029934..edfba93 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -31,6 +31,30 @@ config MV643XX_ETH
 	  Some boards that use the Discovery chipset are the Momenco
 	  Ocelot C and Jaguar ATX and Pegasos II.
 
+config MVMDIO
+	tristate "Marvell MDIO interface support"
+	---help---
+	  This driver supports the MDIO interface found in the network
+	  interface units of the Marvell EBU SoCs (Kirkwood, Orion5x,
+	  Dove, Armada 370 and Armada XP).
+
+	  For now, this driver is only needed for the MVNETA driver
+	  (used on Armada 370 and XP), but it could be used in the
+	  future by the MV643XX_ETH driver.
+
+config MVNETA
+	tristate "Marvell Armada 370/XP network interface support"
+	depends on MACH_ARMADA_370_XP
+	select PHYLIB
+	select MVMDIO
+	---help---
+	  This driver supports the network interface units in the
+	  Marvell ARMADA XP and ARMADA 370 SoC family.
+
+	  Note that this driver is distinct from the mv643xx_eth
+	  driver, which should be used for the older Marvell SoCs
+	  (Dove, Orion, Discovery, Kirkwood).
+
 config PXA168_ETH
 	tristate "Marvell pxa168 ethernet support"
 	depends on CPU_PXA168
diff --git a/drivers/net/ethernet/marvell/Makefile b/drivers/net/ethernet/marvell/Makefile
index 57e3234..7f63b4a 100644
--- a/drivers/net/ethernet/marvell/Makefile
+++ b/drivers/net/ethernet/marvell/Makefile
@@ -3,6 +3,8 @@
 #
 
 obj-$(CONFIG_MV643XX_ETH) += mv643xx_eth.o
+obj-$(CONFIG_MVMDIO) += mvmdio.o
+obj-$(CONFIG_MVNETA) += mvneta.o
 obj-$(CONFIG_PXA168_ETH) += pxa168_eth.o
 obj-$(CONFIG_SKGE) += skge.o
 obj-$(CONFIG_SKY2) += sky2.o
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
new file mode 100644
index 0000000..6d6002b
--- /dev/null
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -0,0 +1,228 @@
+/*
+ * Driver for the MDIO interface of Marvell network interfaces.
+ *
+ * Since the MDIO interface of Marvell network interfaces is shared
+ * between all network interfaces, having a single driver allows to
+ * handle concurrent accesses properly (you may have four Ethernet
+ * ports, but they in fact share the same SMI interface to access the
+ * MDIO bus). Moreover, this MDIO interface code is similar between
+ * the mv643xx_eth driver and the mvneta driver. For now, it is only
+ * used by the mvneta driver, but it could later be used by the
+ * mv643xx_eth driver as well.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/phy.h>
+#include <linux/of_address.h>
+#include <linux/of_mdio.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+
+#define MVMDIO_SMI_DATA_SHIFT              0
+#define MVMDIO_SMI_PHY_ADDR_SHIFT          16
+#define MVMDIO_SMI_PHY_REG_SHIFT           21
+#define MVMDIO_SMI_READ_OPERATION          BIT(26)
+#define MVMDIO_SMI_WRITE_OPERATION         0
+#define MVMDIO_SMI_READ_VALID              BIT(27)
+#define MVMDIO_SMI_BUSY                    BIT(28)
+
+struct orion_mdio_dev {
+	struct mutex lock;
+	void __iomem *smireg;
+};
+
+/* Wait for the SMI unit to be ready for another operation
+ */
+static int orion_mdio_wait_ready(struct mii_bus *bus)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	int count;
+	u32 val;
+
+	count = 0;
+	while (1) {
+		val = readl(dev->smireg);
+		if (!(val & MVMDIO_SMI_BUSY))
+			break;
+
+		if (count > 100) {
+			dev_err(bus->parent, "Timeout: SMI busy for too long\n");
+			return -ETIMEDOUT;
+		}
+
+		udelay(10);
+		count++;
+	}
+
+	return 0;
+}
+
+static int orion_mdio_read(struct mii_bus *bus, int mii_id,
+			   int regnum)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	int count;
+	u32 val;
+	int ret;
+
+	mutex_lock(&dev->lock);
+
+	ret = orion_mdio_wait_ready(bus);
+	if (ret < 0) {
+		mutex_unlock(&dev->lock);
+		return ret;
+	}
+
+	writel(((mii_id << MVMDIO_SMI_PHY_ADDR_SHIFT) |
+		(regnum << MVMDIO_SMI_PHY_REG_SHIFT)  |
+		MVMDIO_SMI_READ_OPERATION),
+	       dev->smireg);
+
+	/* Wait for the value to become available */
+	count = 0;
+	while (1) {
+		val = readl(dev->smireg);
+		if (val & MVMDIO_SMI_READ_VALID)
+			break;
+
+		if (count > 100) {
+			dev_err(bus->parent, "Timeout when reading PHY\n");
+			mutex_unlock(&dev->lock);
+			return -ETIMEDOUT;
+		}
+
+		udelay(10);
+		count++;
+	}
+
+	mutex_unlock(&dev->lock);
+
+	return val & 0xFFFF;
+}
+
+static int orion_mdio_write(struct mii_bus *bus, int mii_id,
+			    int regnum, u16 value)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	int ret;
+
+	mutex_lock(&dev->lock);
+
+	ret = orion_mdio_wait_ready(bus);
+	if (ret < 0) {
+		mutex_unlock(&dev->lock);
+		return ret;
+	}
+
+	writel(((mii_id << MVMDIO_SMI_PHY_ADDR_SHIFT) |
+		(regnum << MVMDIO_SMI_PHY_REG_SHIFT)  |
+		MVMDIO_SMI_WRITE_OPERATION            |
+		(value << MVMDIO_SMI_DATA_SHIFT)),
+	       dev->smireg);
+
+	mutex_unlock(&dev->lock);
+
+	return 0;
+}
+
+static int orion_mdio_reset(struct mii_bus *bus)
+{
+	return 0;
+}
+
+static int __devinit orion_mdio_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct mii_bus *bus;
+	struct orion_mdio_dev *dev;
+	int i, ret;
+
+	bus = mdiobus_alloc_size(sizeof(struct orion_mdio_dev));
+	if (!bus) {
+		dev_err(&pdev->dev, "Cannot allocate MDIO bus\n");
+		return -ENOMEM;
+	}
+
+	bus->name = "orion_mdio_bus";
+	bus->read = orion_mdio_read;
+	bus->write = orion_mdio_write;
+	bus->reset = orion_mdio_reset;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii",
+		 dev_name(&pdev->dev));
+	bus->parent = &pdev->dev;
+
+	bus->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL);
+	if (!bus->irq) {
+		dev_err(&pdev->dev, "Cannot allocate PHY IRQ array\n");
+		mdiobus_free(bus);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < PHY_MAX_ADDR; i++)
+		bus->irq[i] = PHY_POLL;
+
+	dev = bus->priv;
+	dev->smireg = of_iomap(pdev->dev.of_node, 0);
+	if (!dev->smireg) {
+		dev_err(&pdev->dev, "No SMI register address given in DT\n");
+		kfree(bus->irq);
+		mdiobus_free(bus);
+		return -ENODEV;
+	}
+
+	mutex_init(&dev->lock);
+
+	ret = of_mdiobus_register(bus, np);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Cannot register MDIO bus (%d)\n", ret);
+		iounmap(dev->smireg);
+		kfree(bus->irq);
+		mdiobus_free(bus);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, bus);
+
+	return 0;
+}
+
+static int __devexit orion_mdio_remove(struct platform_device *pdev)
+{
+	struct mii_bus *bus = platform_get_drvdata(pdev);
+	mdiobus_unregister(bus);
+	kfree(bus->irq);
+	mdiobus_free(bus);
+	return 0;
+}
+
+static const struct of_device_id orion_mdio_match[] = {
+	{ .compatible = "marvell,orion-mdio" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, orion_mdio_match);
+
+static struct platform_driver orion_mdio_driver = {
+	.probe = orion_mdio_probe,
+	.remove = __devexit_p(orion_mdio_remove),
+	.driver = {
+		.name = "orion-mdio",
+		.of_match_table = orion_mdio_match,
+	},
+};
+
+module_platform_driver(orion_mdio_driver);
+
+MODULE_DESCRIPTION("Marvell MDIO interface driver");
+MODULE_AUTHOR("Thomas Petazzoni <thomas.petazzoni@free-electrons.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
new file mode 100644
index 0000000..3f8086b
--- /dev/null
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -0,0 +1,2848 @@
+/*
+ * Driver for Marvell NETA network card for Armada XP and Armada 370 SoCs.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Rami Rosen <rosenr@marvell.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/version.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/platform_device.h>
+#include <linux/skbuff.h>
+#include <linux/inetdevice.h>
+#include <linux/mbus.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_address.h>
+#include <linux/phy.h>
+#include <linux/clk.h>
+
+/* Registers */
+#define MVNETA_RXQ_CONFIG_REG(q)                (0x1400 + ((q) << 2))
+#define      MVNETA_RXQ_HW_BUF_ALLOC            BIT(1)
+#define      MVNETA_RXQ_PKT_OFFSET_ALL_MASK     (0xf    << 8)
+#define      MVNETA_RXQ_PKT_OFFSET_MASK(offs)   ((offs) << 8)
+#define MVNETA_RXQ_THRESHOLD_REG(q)             (0x14c0 + ((q) << 2))
+#define      MVNETA_RXQ_NON_OCCUPIED(v)         ((v) << 16)
+#define MVNETA_RXQ_BASE_ADDR_REG(q)             (0x1480 + ((q) << 2))
+#define MVNETA_RXQ_SIZE_REG(q)                  (0x14a0 + ((q) << 2))
+#define      MVNETA_RXQ_BUF_SIZE_SHIFT          19
+#define      MVNETA_RXQ_BUF_SIZE_MASK           (0x1fff << 19)
+#define MVNETA_RXQ_STATUS_REG(q)                (0x14e0 + ((q) << 2))
+#define      MVNETA_RXQ_OCCUPIED_ALL_MASK       0x3fff
+#define MVNETA_RXQ_STATUS_UPDATE_REG(q)         (0x1500 + ((q) << 2))
+#define      MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT  16
+#define      MVNETA_RXQ_ADD_NON_OCCUPIED_MAX    255
+#define MVNETA_PORT_RX_RESET                    0x1cc0
+#define      MVNETA_PORT_RX_DMA_RESET           BIT(0)
+#define MVNETA_PHY_ADDR                         0x2000
+#define      MVNETA_PHY_ADDR_MASK               0x1f
+#define MVNETA_MBUS_RETRY                       0x2010
+#define MVNETA_UNIT_INTR_CAUSE                  0x2080
+#define MVNETA_UNIT_CONTROL                     0x20B0
+#define      MVNETA_PHY_POLLING_ENABLE          BIT(1)
+#define MVNETA_WIN_BASE(w)                      (0x2200 + ((w) << 3))
+#define MVNETA_WIN_SIZE(w)                      (0x2204 + ((w) << 3))
+#define MVNETA_WIN_REMAP(w)                     (0x2280 + ((w) << 2))
+#define MVNETA_BASE_ADDR_ENABLE                 0x2290
+#define MVNETA_PORT_CONFIG                      0x2400
+#define      MVNETA_UNI_PROMISC_MODE            BIT(0)
+#define      MVNETA_DEF_RXQ(q)                  ((q) << 1)
+#define      MVNETA_DEF_RXQ_ARP(q)              ((q) << 4)
+#define      MVNETA_TX_UNSET_ERR_SUM            BIT(12)
+#define      MVNETA_DEF_RXQ_TCP(q)              ((q) << 16)
+#define      MVNETA_DEF_RXQ_UDP(q)              ((q) << 19)
+#define      MVNETA_DEF_RXQ_BPDU(q)             ((q) << 22)
+#define      MVNETA_RX_CSUM_WITH_PSEUDO_HDR     BIT(25)
+#define      MVNETA_PORT_CONFIG_DEFL_VALUE(q)   (MVNETA_DEF_RXQ(q)       | \
+						 MVNETA_DEF_RXQ_ARP(q)	 | \
+						 MVNETA_DEF_RXQ_TCP(q)	 | \
+						 MVNETA_DEF_RXQ_UDP(q)	 | \
+						 MVNETA_DEF_RXQ_BPDU(q)	 | \
+						 MVNETA_TX_UNSET_ERR_SUM | \
+						 MVNETA_RX_CSUM_WITH_PSEUDO_HDR)
+#define MVNETA_PORT_CONFIG_EXTEND                0x2404
+#define MVNETA_MAC_ADDR_LOW                      0x2414
+#define MVNETA_MAC_ADDR_HIGH                     0x2418
+#define MVNETA_SDMA_CONFIG                       0x241c
+#define      MVNETA_SDMA_BRST_SIZE_16            4
+#define      MVNETA_NO_DESC_SWAP                 0x0
+#define      MVNETA_RX_BRST_SZ_MASK(burst)       ((burst) << 1)
+#define      MVNETA_RX_NO_DATA_SWAP              BIT(4)
+#define      MVNETA_TX_NO_DATA_SWAP              BIT(5)
+#define      MVNETA_TX_BRST_SZ_MASK(burst)       ((burst) << 22)
+#define MVNETA_PORT_STATUS                       0x2444
+#define      MVNETA_TX_IN_PRGRS                  BIT(1)
+#define      MVNETA_TX_FIFO_EMPTY                BIT(8)
+#define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
+#define MVNETA_TYPE_PRIO                         0x24bc
+#define      MVNETA_FORCE_UNI                    BIT(21)
+#define MVNETA_TXQ_CMD_1                         0x24e4
+#define MVNETA_TXQ_CMD                           0x2448
+#define      MVNETA_TXQ_DISABLE_SHIFT            8
+#define      MVNETA_TXQ_ENABLE_MASK              0x000000ff
+#define MVNETA_ACC_MODE                          0x2500
+#define MVNETA_CPU_MAP(cpu)                      (0x2540 + ((cpu) << 2))
+#define      MVNETA_CPU_RXQ_ACCESS_ALL_MASK      0x000000ff
+#define      MVNETA_CPU_TXQ_ACCESS_ALL_MASK      0x0000ff00
+#define MVNETA_RXQ_TIME_COAL_REG(q)              (0x2580 + ((q) << 2))
+#define MVNETA_INTR_NEW_CAUSE                    0x25a0
+#define      MVNETA_RX_INTR_MASK(nr_rxqs)        (((1 << nr_rxqs) - 1) << 8)
+#define MVNETA_INTR_NEW_MASK                     0x25a4
+#define MVNETA_INTR_OLD_CAUSE                    0x25a8
+#define MVNETA_INTR_OLD_MASK                     0x25ac
+#define MVNETA_INTR_MISC_CAUSE                   0x25b0
+#define MVNETA_INTR_MISC_MASK                    0x25b4
+#define MVNETA_INTR_ENABLE                       0x25b8
+#define      MVNETA_TXQ_INTR_ENABLE_ALL_MASK     0x0000ff00
+#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0xff000000
+#define MVNETA_RXQ_CMD                           0x2680
+#define      MVNETA_RXQ_DISABLE_SHIFT            8
+#define      MVNETA_RXQ_ENABLE_MASK              0x000000ff
+#define MVETH_TXQ_TOKEN_COUNT_REG(q)             (0x2700 + ((q) << 4))
+#define MVETH_TXQ_TOKEN_CFG_REG(q)               (0x2704 + ((q) << 4))
+#define MVNETA_GMAC_CTRL_0                       0x2c00
+#define      MVNETA_GMAC_MAX_RX_SIZE_SHIFT       2
+#define      MVNETA_GMAC_MAX_RX_SIZE_MASK        0x7ffc
+#define      MVNETA_GMAC0_PORT_ENABLE            BIT(0)
+#define MVNETA_GMAC_CTRL_2                       0x2c08
+#define      MVNETA_GMAC2_PSC_ENABLE             BIT(3)
+#define      MVNETA_GMAC2_PORT_RGMII             BIT(4)
+#define      MVNETA_GMAC2_PORT_RESET             BIT(6)
+#define MVNETA_GMAC_STATUS                       0x2c10
+#define      MVNETA_GMAC_LINK_UP                 BIT(0)
+#define      MVNETA_GMAC_SPEED_1000              BIT(1)
+#define      MVNETA_GMAC_SPEED_100               BIT(2)
+#define      MVNETA_GMAC_FULL_DUPLEX             BIT(3)
+#define      MVNETA_GMAC_RX_FLOW_CTRL_ENABLE     BIT(4)
+#define      MVNETA_GMAC_TX_FLOW_CTRL_ENABLE     BIT(5)
+#define      MVNETA_GMAC_RX_FLOW_CTRL_ACTIVE     BIT(6)
+#define      MVNETA_GMAC_TX_FLOW_CTRL_ACTIVE     BIT(7)
+#define MVNETA_GMAC_AUTONEG_CONFIG               0x2c0c
+#define      MVNETA_GMAC_FORCE_LINK_DOWN         BIT(0)
+#define      MVNETA_GMAC_FORCE_LINK_PASS         BIT(1)
+#define      MVNETA_GMAC_CONFIG_MII_SPEED        BIT(5)
+#define      MVNETA_GMAC_CONFIG_GMII_SPEED       BIT(6)
+#define      MVNETA_GMAC_CONFIG_FULL_DUPLEX      BIT(12)
+#define MVNETA_MIB_COUNTERS_BASE                 0x3080
+#define      MVNETA_MIB_LATE_COLLISION           0x7c
+#define MVNETA_DA_FILT_SPEC_MCAST                0x3400
+#define MVNETA_DA_FILT_OTH_MCAST                 0x3500
+#define MVNETA_DA_FILT_UCAST_BASE                0x3600
+#define MVNETA_TXQ_BASE_ADDR_REG(q)              (0x3c00 + ((q) << 2))
+#define MVNETA_TXQ_SIZE_REG(q)                   (0x3c20 + ((q) << 2))
+#define      MVNETA_TXQ_SENT_THRESH_ALL_MASK     0x3fff0000
+#define      MVNETA_TXQ_SENT_THRESH_MASK(coal)   ((coal) << 16)
+#define MVNETA_TXQ_UPDATE_REG(q)                 (0x3c60 + ((q) << 2))
+#define      MVNETA_TXQ_DEC_SENT_SHIFT           16
+#define MVNETA_TXQ_STATUS_REG(q)                 (0x3c40 + ((q) << 2))
+#define      MVNETA_TXQ_SENT_DESC_SHIFT          16
+#define      MVNETA_TXQ_SENT_DESC_MASK           0x3fff0000
+#define MVNETA_PORT_TX_RESET                     0x3cf0
+#define      MVNETA_PORT_TX_DMA_RESET            BIT(0)
+#define MVNETA_TX_MTU                            0x3e0c
+#define MVNETA_TX_TOKEN_SIZE                     0x3e14
+#define      MVNETA_TX_TOKEN_SIZE_MAX            0xffffffff
+#define MVNETA_TXQ_TOKEN_SIZE_REG(q)             (0x3e40 + ((q) << 2))
+#define      MVNETA_TXQ_TOKEN_SIZE_MAX           0x7fffffff
+
+#define MVNETA_CAUSE_TXQ_SENT_DESC_ALL_MASK	 0xff
+
+/* Descriptor ring Macros */
+#define MVNETA_QUEUE_NEXT_DESC(q, index)	\
+	(((index) < (q)->last_desc) ? ((index) + 1) : 0)
+
+/* Various constants */
+
+/* Coalescing */
+#define MVNETA_TXDONE_COAL_PKTS		16
+#define MVNETA_RX_COAL_PKTS		32
+#define MVNETA_RX_COAL_USEC		100
+
+/* Timer */
+#define MVNETA_TX_DONE_TIMER_PERIOD	10
+
+/* Napi polling weight */
+#define MVNETA_RX_POLL_WEIGHT		64
+
+/* The two bytes Marvell header. Either contains a special value used
+ * by Marvell switches when a specific hardware mode is enabled (not
+ * supported by this driver) or is filled automatically by zeroes on
+ * the RX side. Those two bytes being at the front of the Ethernet
+ * header, they allow to have the IP header aligned on a 4 bytes
+ * boundary automatically: the hardware skips those two bytes on its
+ * own.
+ */
+#define MVNETA_MH_SIZE			2
+
+#define MVNETA_VLAN_TAG_LEN             4
+
+#define MVNETA_CPU_D_CACHE_LINE_SIZE    32
+#define MVNETA_TX_CSUM_MAX_SIZE		9800
+#define MVNETA_ACC_MODE_EXT		1
+
+/* Timeout constants */
+#define MVNETA_TX_DISABLE_TIMEOUT_MSEC	1000
+#define MVNETA_RX_DISABLE_TIMEOUT_MSEC	1000
+#define MVNETA_TX_FIFO_EMPTY_TIMEOUT	10000
+
+#define MVNETA_TX_MTU_MAX		0x3ffff
+
+/* Max number of Rx descriptors */
+#define MVNETA_MAX_RXD 128
+
+/* Max number of Tx descriptors */
+#define MVNETA_MAX_TXD 532
+
+/* descriptor aligned size */
+#define MVNETA_DESC_ALIGNED_SIZE	32
+
+#define MVNETA_RX_PKT_SIZE(mtu) \
+	ALIGN((mtu) + MVNETA_MH_SIZE + MVNETA_VLAN_TAG_LEN + \
+	      ETH_HLEN + ETH_FCS_LEN,			     \
+	      MVNETA_CPU_D_CACHE_LINE_SIZE)
+
+#define MVNETA_RX_BUF_SIZE(pkt_size)   ((pkt_size) + NET_SKB_PAD)
+
+struct mvneta_stats {
+	struct	u64_stats_sync syncp;
+	u64	packets;
+	u64	bytes;
+};
+
+struct mvneta_port {
+	int pkt_size;
+	void __iomem *base;
+	struct mvneta_rx_queue *rxqs;
+	struct mvneta_tx_queue *txqs;
+	struct timer_list tx_done_timer;
+	struct net_device *dev;
+
+	u32 cause_rx_tx;
+	struct napi_struct napi;
+
+	/* Flags */
+	unsigned long flags;
+#define MVNETA_F_TX_DONE_TIMER_BIT  0
+
+	/* Napi weight */
+	int weight;
+
+	/* Core clock */
+	struct clk *clk;
+	u8 mcast_count[256];
+	u16 tx_ring_size;
+	u16 rx_ring_size;
+	struct mvneta_stats tx_stats;
+	struct mvneta_stats rx_stats;
+
+	struct mii_bus *mii_bus;
+	struct phy_device *phy_dev;
+	phy_interface_t phy_interface;
+	struct device_node *phy_node;
+	unsigned int link;
+	unsigned int duplex;
+	unsigned int speed;
+};
+
+/* The mvneta_tx_desc and mvneta_rx_desc structures describe the
+ * layout of the transmit and reception DMA descriptors, and their
+ * layout is therefore defined by the hardware design
+ */
+struct mvneta_tx_desc {
+	u32  command;		/* Options used by HW for packet transmitting.*/
+#define MVNETA_TX_L3_OFF_SHIFT	0
+#define MVNETA_TX_IP_HLEN_SHIFT	8
+#define MVNETA_TX_L4_UDP	BIT(16)
+#define MVNETA_TX_L3_IP6	BIT(17)
+#define MVNETA_TXD_IP_CSUM	BIT(18)
+#define MVNETA_TXD_Z_PAD	BIT(19)
+#define MVNETA_TXD_L_DESC	BIT(20)
+#define MVNETA_TXD_F_DESC	BIT(21)
+#define MVNETA_TXD_FLZ_DESC	(MVNETA_TXD_Z_PAD  | \
+				 MVNETA_TXD_L_DESC | \
+				 MVNETA_TXD_F_DESC)
+#define MVNETA_TX_L4_CSUM_FULL	BIT(30)
+#define MVNETA_TX_L4_CSUM_NOT	BIT(31)
+
+	u16  reserverd1;	/* csum_l4 (for future use)		*/
+	u16  data_size;		/* Data size of transmitted packet in bytes */
+	u32  buf_phys_addr;	/* Physical addr of transmitted buffer	*/
+	u32  reserved2;		/* hw_cmd - (for future use, PMT)	*/
+	u32  reserved3[4];	/* Reserved - (for future use)		*/
+};
+
+struct mvneta_rx_desc {
+	u32  status;		/* Info about received packet		*/
+#define MVNETA_RXD_ERR_CRC		0x0
+#define MVNETA_RXD_ERR_SUMMARY		BIT(16)
+#define MVNETA_RXD_ERR_OVERRUN		BIT(17)
+#define MVNETA_RXD_ERR_LEN		BIT(18)
+#define MVNETA_RXD_ERR_RESOURCE		(BIT(17) | BIT(18))
+#define MVNETA_RXD_ERR_CODE_MASK	(BIT(17) | BIT(18))
+#define MVNETA_RXD_L3_IP4		BIT(25)
+#define MVNETA_RXD_FIRST_LAST_DESC	(BIT(26) | BIT(27))
+#define MVNETA_RXD_L4_CSUM_OK		BIT(30)
+
+	u16  reserved1;		/* pnc_info - (for future use, PnC)	*/
+	u16  data_size;		/* Size of received packet in bytes	*/
+	u32  buf_phys_addr;	/* Physical address of the buffer	*/
+	u32  reserved2;		/* pnc_flow_id  (for future use, PnC)	*/
+	u32  buf_cookie;	/* cookie for access to RX buffer in rx path */
+	u16  reserved3;		/* prefetch_cmd, for future use		*/
+	u16  reserved4;		/* csum_l4 - (for future use, PnC)	*/
+	u32  reserved5;		/* pnc_extra PnC (for future use, PnC)	*/
+	u32  reserved6;		/* hw_cmd (for future use, PnC and HWF)	*/
+};
+
+struct mvneta_tx_queue {
+	/* Number of this TX queue, in the range 0-7 */
+	u8 id;
+
+	/* Number of TX DMA descriptors in the descriptor ring */
+	int size;
+
+	/* Number of currently used TX DMA descriptor in the
+	 * descriptor ring
+	 */
+	int count;
+
+	/* Array of transmitted skb */
+	struct sk_buff **tx_skb;
+
+	/* Index of last TX DMA descriptor that was inserted */
+	int txq_put_index;
+
+	/* Index of the TX DMA descriptor to be cleaned up */
+	int txq_get_index;
+
+	u32 done_pkts_coal;
+
+	/* Virtual address of the TX DMA descriptors array */
+	struct mvneta_tx_desc *descs;
+
+	/* DMA address of the TX DMA descriptors array */
+	dma_addr_t descs_phys;
+
+	/* Index of the last TX DMA descriptor */
+	int last_desc;
+
+	/* Index of the next TX DMA descriptor to process */
+	int next_desc_to_proc;
+};
+
+struct mvneta_rx_queue {
+	/* rx queue number, in the range 0-7 */
+	u8 id;
+
+	/* num of rx descriptors in the rx descriptor ring */
+	int size;
+
+	/* counter of times when mvneta_refill() failed */
+	int missed;
+
+	u32 pkts_coal;
+	u32 time_coal;
+
+	/* Virtual address of the RX DMA descriptors array */
+	struct mvneta_rx_desc *descs;
+
+	/* DMA address of the RX DMA descriptors array */
+	dma_addr_t descs_phys;
+
+	/* Index of the last RX DMA descriptor */
+	int last_desc;
+
+	/* Index of the next RX DMA descriptor to process */
+	int next_desc_to_proc;
+};
+
+static int rxq_number = 8;
+static int txq_number = 8;
+
+static int rxq_def;
+static int txq_def;
+
+#define MVNETA_DRIVER_NAME "mvneta"
+#define MVNETA_DRIVER_VERSION "1.0"
+
+/* Utility/helper methods */
+
+/* Write helper method */
+static void mvreg_write(struct mvneta_port *pp, u32 offset, u32 data)
+{
+	writel(data, pp->base + offset);
+}
+
+/* Read helper method */
+static u32 mvreg_read(struct mvneta_port *pp, u32 offset)
+{
+	return readl(pp->base + offset);
+}
+
+/* Increment txq get counter */
+static void mvneta_txq_inc_get(struct mvneta_tx_queue *txq)
+{
+	txq->txq_get_index++;
+	if (txq->txq_get_index == txq->size)
+		txq->txq_get_index = 0;
+}
+
+/* Increment txq put counter */
+static void mvneta_txq_inc_put(struct mvneta_tx_queue *txq)
+{
+	txq->txq_put_index++;
+	if (txq->txq_put_index == txq->size)
+		txq->txq_put_index = 0;
+}
+
+
+/* Clear all MIB counters */
+static void mvneta_mib_counters_clear(struct mvneta_port *pp)
+{
+	int i;
+	u32 dummy;
+
+	/* Perform dummy reads from MIB counters */
+	for (i = 0; i < MVNETA_MIB_LATE_COLLISION; i += 4)
+		dummy = mvreg_read(pp, (MVNETA_MIB_COUNTERS_BASE + i));
+}
+
+/* Get System Network Statistics */
+struct rtnl_link_stats64 *mvneta_get_stats64(struct net_device *dev,
+					     struct rtnl_link_stats64 *stats)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+	unsigned int start;
+
+	memset(stats, 0, sizeof(struct rtnl_link_stats64));
+
+	do {
+		start = u64_stats_fetch_begin_bh(&pp->rx_stats.syncp);
+		stats->rx_packets = pp->rx_stats.packets;
+		stats->rx_bytes	= pp->rx_stats.bytes;
+	} while (u64_stats_fetch_retry_bh(&pp->rx_stats.syncp, start));
+
+
+	do {
+		start = u64_stats_fetch_begin_bh(&pp->tx_stats.syncp);
+		stats->tx_packets = pp->tx_stats.packets;
+		stats->tx_bytes	= pp->tx_stats.bytes;
+	} while (u64_stats_fetch_retry_bh(&pp->tx_stats.syncp, start));
+
+	stats->rx_errors	= dev->stats.rx_errors;
+	stats->rx_dropped	= dev->stats.rx_dropped;
+
+	stats->tx_dropped	= dev->stats.tx_dropped;
+
+	return stats;
+}
+
+/* Rx descriptors helper methods */
+
+/* Checks whether the given RX descriptor is both the first and the
+ * last descriptor for the RX packet. Each RX packet is currently
+ * received through a single RX descriptor, so not having each RX
+ * descriptor with its first and last bits set is an error
+ */
+static int mvneta_rxq_desc_is_first_last(struct mvneta_rx_desc *desc)
+{
+	return (desc->status & MVNETA_RXD_FIRST_LAST_DESC) ==
+		MVNETA_RXD_FIRST_LAST_DESC;
+}
+
+/* Add number of descriptors ready to receive new packets */
+static void mvneta_rxq_non_occup_desc_add(struct mvneta_port *pp,
+					  struct mvneta_rx_queue *rxq,
+					  int ndescs)
+{
+	/* Only MVNETA_RXQ_ADD_NON_OCCUPIED_MAX (255) descriptors can
+	 * be added at once
+	 */
+	while (ndescs > MVNETA_RXQ_ADD_NON_OCCUPIED_MAX) {
+		mvreg_write(pp, MVNETA_RXQ_STATUS_UPDATE_REG(rxq->id),
+			    (MVNETA_RXQ_ADD_NON_OCCUPIED_MAX <<
+			     MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT));
+		ndescs -= MVNETA_RXQ_ADD_NON_OCCUPIED_MAX;
+	}
+
+	mvreg_write(pp, MVNETA_RXQ_STATUS_UPDATE_REG(rxq->id),
+		    (ndescs << MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT));
+}
+
+/* Get number of RX descriptors occupied by received packets */
+static int mvneta_rxq_busy_desc_num_get(struct mvneta_port *pp,
+					struct mvneta_rx_queue *rxq)
+{
+	u32 val;
+
+	val = mvreg_read(pp, MVNETA_RXQ_STATUS_REG(rxq->id));
+	return val & MVNETA_RXQ_OCCUPIED_ALL_MASK;
+}
+
+/* Update num of rx desc called upon return from rx path or
+ * from mvneta_rxq_drop_pkts().
+ */
+static void mvneta_rxq_desc_num_update(struct mvneta_port *pp,
+				       struct mvneta_rx_queue *rxq,
+				       int rx_done, int rx_filled)
+{
+	u32 val;
+
+	if ((rx_done <= 0xff) && (rx_filled <= 0xff)) {
+		val = rx_done |
+		  (rx_filled << MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT);
+		mvreg_write(pp, MVNETA_RXQ_STATUS_UPDATE_REG(rxq->id), val);
+		return;
+	}
+
+	/* Only 255 descriptors can be added at once */
+	while ((rx_done > 0) || (rx_filled > 0)) {
+		if (rx_done <= 0xff) {
+			val = rx_done;
+			rx_done = 0;
+		} else {
+			val = 0xff;
+			rx_done -= 0xff;
+		}
+		if (rx_filled <= 0xff) {
+			val |= rx_filled << MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT;
+			rx_filled = 0;
+		} else {
+			val |= 0xff << MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT;
+			rx_filled -= 0xff;
+		}
+		mvreg_write(pp, MVNETA_RXQ_STATUS_UPDATE_REG(rxq->id), val);
+	}
+}
+
+/* Get pointer to next RX descriptor to be processed by SW */
+static struct mvneta_rx_desc *
+mvneta_rxq_next_desc_get(struct mvneta_rx_queue *rxq)
+{
+	int rx_desc = rxq->next_desc_to_proc;
+
+	rxq->next_desc_to_proc = MVNETA_QUEUE_NEXT_DESC(rxq, rx_desc);
+	return rxq->descs + rx_desc;
+}
+
+/* Change maximum receive size of the port. */
+static void mvneta_max_rx_size_set(struct mvneta_port *pp, int max_rx_size)
+{
+	u32 val;
+
+	val =  mvreg_read(pp, MVNETA_GMAC_CTRL_0);
+	val &= ~MVNETA_GMAC_MAX_RX_SIZE_MASK;
+	val |= ((max_rx_size - MVNETA_MH_SIZE) / 2) <<
+		MVNETA_GMAC_MAX_RX_SIZE_SHIFT;
+	mvreg_write(pp, MVNETA_GMAC_CTRL_0, val);
+}
+
+
+/* Set rx queue offset */
+static void mvneta_rxq_offset_set(struct mvneta_port *pp,
+				  struct mvneta_rx_queue *rxq,
+				  int offset)
+{
+	u32 val;
+
+	val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
+	val &= ~MVNETA_RXQ_PKT_OFFSET_ALL_MASK;
+
+	/* Offset is in */
+	val |= MVNETA_RXQ_PKT_OFFSET_MASK(offset >> 3);
+	mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
+}
+
+
+/* Tx descriptors helper methods */
+
+/* Update HW with number of TX descriptors to be sent */
+static void mvneta_txq_pend_desc_add(struct mvneta_port *pp,
+				     struct mvneta_tx_queue *txq,
+				     int pend_desc)
+{
+	u32 val;
+
+	/* Only 255 descriptors can be added at once ; Assume caller
+	 * process TX desriptors in quanta less than 256
+	 */
+	val = pend_desc;
+	mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
+}
+
+/* Get pointer to next TX descriptor to be processed (send) by HW */
+static struct mvneta_tx_desc *
+mvneta_txq_next_desc_get(struct mvneta_tx_queue *txq)
+{
+	int tx_desc = txq->next_desc_to_proc;
+
+	txq->next_desc_to_proc = MVNETA_QUEUE_NEXT_DESC(txq, tx_desc);
+	return txq->descs + tx_desc;
+}
+
+/* Release the last allocated TX descriptor. Useful to handle DMA
+ * mapping failures in the TX path.
+ */
+static void mvneta_txq_desc_put(struct mvneta_tx_queue *txq)
+{
+	if (txq->next_desc_to_proc == 0)
+		txq->next_desc_to_proc = txq->last_desc - 1;
+	else
+		txq->next_desc_to_proc--;
+}
+
+/* Set rxq buf size */
+static void mvneta_rxq_buf_size_set(struct mvneta_port *pp,
+				    struct mvneta_rx_queue *rxq,
+				    int buf_size)
+{
+	u32 val;
+
+	val = mvreg_read(pp, MVNETA_RXQ_SIZE_REG(rxq->id));
+
+	val &= ~MVNETA_RXQ_BUF_SIZE_MASK;
+	val |= ((buf_size >> 3) << MVNETA_RXQ_BUF_SIZE_SHIFT);
+
+	mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), val);
+}
+
+/* Disable buffer management (BM) */
+static void mvneta_rxq_bm_disable(struct mvneta_port *pp,
+				  struct mvneta_rx_queue *rxq)
+{
+	u32 val;
+
+	val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
+	val &= ~MVNETA_RXQ_HW_BUF_ALLOC;
+	mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
+}
+
+
+
+/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */
+static void __devinit mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable)
+{
+	u32  val;
+
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+
+	if (enable)
+		val |= MVNETA_GMAC2_PORT_RGMII;
+	else
+		val &= ~MVNETA_GMAC2_PORT_RGMII;
+
+	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+}
+
+/* Config SGMII port */
+static void __devinit mvneta_port_sgmii_config(struct mvneta_port *pp)
+{
+	u32 val;
+
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+	val |= MVNETA_GMAC2_PSC_ENABLE;
+	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+}
+
+/* Start the Ethernet port RX and TX activity */
+static void mvneta_port_up(struct mvneta_port *pp)
+{
+	int queue;
+	u32 q_map;
+
+	/* Enable all initialized TXs. */
+	mvneta_mib_counters_clear(pp);
+	q_map = 0;
+	for (queue = 0; queue < txq_number; queue++) {
+		struct mvneta_tx_queue *txq = &pp->txqs[queue];
+		if (txq->descs != NULL)
+			q_map |= (1 << queue);
+	}
+	mvreg_write(pp, MVNETA_TXQ_CMD, q_map);
+
+	/* Enable all initialized RXQs. */
+	q_map = 0;
+	for (queue = 0; queue < rxq_number; queue++) {
+		struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
+		if (rxq->descs != NULL)
+			q_map |= (1 << queue);
+	}
+
+	mvreg_write(pp, MVNETA_RXQ_CMD, q_map);
+}
+
+/* Stop the Ethernet port activity */
+static void mvneta_port_down(struct mvneta_port *pp)
+{
+	u32 val;
+	int count;
+
+	/* Stop Rx port activity. Check port Rx activity. */
+	val = mvreg_read(pp, MVNETA_RXQ_CMD) & MVNETA_RXQ_ENABLE_MASK;
+
+	/* Issue stop command for active channels only */
+	if (val != 0)
+		mvreg_write(pp, MVNETA_RXQ_CMD,
+			    val << MVNETA_RXQ_DISABLE_SHIFT);
+
+	/* Wait for all Rx activity to terminate. */
+	count = 0;
+	do {
+		if (count++ >= MVNETA_RX_DISABLE_TIMEOUT_MSEC) {
+			netdev_warn(pp->dev,
+				    "TIMEOUT for RX stopped ! rx_queue_cmd: 0x08%x\n",
+				    val);
+			break;
+		}
+		mdelay(1);
+
+		val = mvreg_read(pp, MVNETA_RXQ_CMD);
+	} while (val & 0xff);
+
+	/* Stop Tx port activity. Check port Tx activity. Issue stop
+	 * command for active channels only
+	 */
+	val = (mvreg_read(pp, MVNETA_TXQ_CMD)) & MVNETA_TXQ_ENABLE_MASK;
+
+	if (val != 0)
+		mvreg_write(pp, MVNETA_TXQ_CMD,
+			    (val << MVNETA_TXQ_DISABLE_SHIFT));
+
+	/* Wait for all Tx activity to terminate. */
+	count = 0;
+	do {
+		if (count++ >= MVNETA_TX_DISABLE_TIMEOUT_MSEC) {
+			netdev_warn(pp->dev,
+				    "TIMEOUT for TX stopped status=0x%08x\n",
+				    val);
+			break;
+		}
+		mdelay(1);
+
+		/* Check TX Command reg that all Txqs are stopped */
+		val = mvreg_read(pp, MVNETA_TXQ_CMD);
+
+	} while (val & 0xff);
+
+	/* Double check to verify that TX FIFO is empty */
+	count = 0;
+	do {
+		if (count++ >= MVNETA_TX_FIFO_EMPTY_TIMEOUT) {
+			netdev_warn(pp->dev,
+				    "TX FIFO empty timeout status=0x08%x\n",
+				    val);
+			break;
+		}
+		mdelay(1);
+
+		val = mvreg_read(pp, MVNETA_PORT_STATUS);
+	} while (!(val & MVNETA_TX_FIFO_EMPTY) &&
+		 (val & MVNETA_TX_IN_PRGRS));
+
+	udelay(200);
+}
+
+/* Enable the port by setting the port enable bit of the MAC control register */
+static void mvneta_port_enable(struct mvneta_port *pp)
+{
+	u32 val;
+
+	/* Enable port */
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_0);
+	val |= MVNETA_GMAC0_PORT_ENABLE;
+	mvreg_write(pp, MVNETA_GMAC_CTRL_0, val);
+}
+
+/* Disable the port and wait for about 200 usec before retuning */
+static void mvneta_port_disable(struct mvneta_port *pp)
+{
+	u32 val;
+
+	/* Reset the Enable bit in the Serial Control Register */
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_0);
+	val &= ~MVNETA_GMAC0_PORT_ENABLE;
+	mvreg_write(pp, MVNETA_GMAC_CTRL_0, val);
+
+	udelay(200);
+}
+
+/* Multicast tables methods */
+
+/* Set all entries in Unicast MAC Table; queue==-1 means reject all */
+static void mvneta_set_ucast_table(struct mvneta_port *pp, int queue)
+{
+	int offset;
+	u32 val;
+
+	if (queue == -1) {
+		val = 0;
+	} else {
+		val = 0x1 | (queue << 1);
+		val |= (val << 24) | (val << 16) | (val << 8);
+	}
+
+	for (offset = 0; offset <= 0xc; offset += 4)
+		mvreg_write(pp, MVNETA_DA_FILT_UCAST_BASE + offset, val);
+}
+
+/* Set all entries in Special Multicast MAC Table; queue==-1 means reject all */
+static void mvneta_set_special_mcast_table(struct mvneta_port *pp, int queue)
+{
+	int offset;
+	u32 val;
+
+	if (queue == -1) {
+		val = 0;
+	} else {
+		val = 0x1 | (queue << 1);
+		val |= (val << 24) | (val << 16) | (val << 8);
+	}
+
+	for (offset = 0; offset <= 0xfc; offset += 4)
+		mvreg_write(pp, MVNETA_DA_FILT_SPEC_MCAST + offset, val);
+
+}
+
+/* Set all entries in Other Multicast MAC Table. queue==-1 means reject all */
+static void mvneta_set_other_mcast_table(struct mvneta_port *pp, int queue)
+{
+	int offset;
+	u32 val;
+
+	if (queue == -1) {
+		memset(pp->mcast_count, 0, sizeof(pp->mcast_count));
+		val = 0;
+	} else {
+		memset(pp->mcast_count, 1, sizeof(pp->mcast_count));
+		val = 0x1 | (queue << 1);
+		val |= (val << 24) | (val << 16) | (val << 8);
+	}
+
+	for (offset = 0; offset <= 0xfc; offset += 4)
+		mvreg_write(pp, MVNETA_DA_FILT_OTH_MCAST + offset, val);
+}
+
+/* This method sets defaults to the NETA port:
+ *	Clears interrupt Cause and Mask registers.
+ *	Clears all MAC tables.
+ *	Sets defaults to all registers.
+ *	Resets RX and TX descriptor rings.
+ *	Resets PHY.
+ * This method can be called after mvneta_port_down() to return the port
+ *	settings to defaults.
+ */
+static void mvneta_defaults_set(struct mvneta_port *pp)
+{
+	int cpu;
+	int queue;
+	u32 val;
+
+	/* Clear all Cause registers */
+	mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
+	mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
+	mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
+
+	/* Mask all interrupts */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_ENABLE, 0);
+
+	/* Enable MBUS Retry bit16 */
+	mvreg_write(pp, MVNETA_MBUS_RETRY, 0x20);
+
+	/* Set CPU queue access map - all CPUs have access to all RX
+	 * queues and to all TX queues
+	 */
+	for (cpu = 0; cpu < CONFIG_NR_CPUS; cpu++)
+		mvreg_write(pp, MVNETA_CPU_MAP(cpu),
+			    (MVNETA_CPU_RXQ_ACCESS_ALL_MASK |
+			     MVNETA_CPU_TXQ_ACCESS_ALL_MASK));
+
+	/* Reset RX and TX DMAs */
+	mvreg_write(pp, MVNETA_PORT_RX_RESET, MVNETA_PORT_RX_DMA_RESET);
+	mvreg_write(pp, MVNETA_PORT_TX_RESET, MVNETA_PORT_TX_DMA_RESET);
+
+	/* Disable Legacy WRR, Disable EJP, Release from reset */
+	mvreg_write(pp, MVNETA_TXQ_CMD_1, 0);
+	for (queue = 0; queue < txq_number; queue++) {
+		mvreg_write(pp, MVETH_TXQ_TOKEN_COUNT_REG(queue), 0);
+		mvreg_write(pp, MVETH_TXQ_TOKEN_CFG_REG(queue), 0);
+	}
+
+	mvreg_write(pp, MVNETA_PORT_TX_RESET, 0);
+	mvreg_write(pp, MVNETA_PORT_RX_RESET, 0);
+
+	/* Set Port Acceleration Mode */
+	val = MVNETA_ACC_MODE_EXT;
+	mvreg_write(pp, MVNETA_ACC_MODE, val);
+
+	/* Update val of portCfg register accordingly with all RxQueue types */
+	val = MVNETA_PORT_CONFIG_DEFL_VALUE(rxq_def);
+	mvreg_write(pp, MVNETA_PORT_CONFIG, val);
+
+	val = 0;
+	mvreg_write(pp, MVNETA_PORT_CONFIG_EXTEND, val);
+	mvreg_write(pp, MVNETA_RX_MIN_FRAME_SIZE, 64);
+
+	/* Build PORT_SDMA_CONFIG_REG */
+	val = 0;
+
+	/* Default burst size */
+	val |= MVNETA_TX_BRST_SZ_MASK(MVNETA_SDMA_BRST_SIZE_16);
+	val |= MVNETA_RX_BRST_SZ_MASK(MVNETA_SDMA_BRST_SIZE_16);
+
+	val |= (MVNETA_RX_NO_DATA_SWAP | MVNETA_TX_NO_DATA_SWAP |
+		MVNETA_NO_DESC_SWAP);
+
+	/* Assign port SDMA configuration */
+	mvreg_write(pp, MVNETA_SDMA_CONFIG, val);
+
+	mvneta_set_ucast_table(pp, -1);
+	mvneta_set_special_mcast_table(pp, -1);
+	mvneta_set_other_mcast_table(pp, -1);
+
+	/* Set port interrupt enable register - default enable all */
+	mvreg_write(pp, MVNETA_INTR_ENABLE,
+		    (MVNETA_RXQ_INTR_ENABLE_ALL_MASK
+		     | MVNETA_TXQ_INTR_ENABLE_ALL_MASK));
+}
+
+/* Set max sizes for tx queues */
+static void mvneta_txq_max_tx_size_set(struct mvneta_port *pp, int max_tx_size)
+
+{
+	u32 val, size, mtu;
+	int queue;
+
+	mtu = max_tx_size * 8;
+	if (mtu > MVNETA_TX_MTU_MAX)
+		mtu = MVNETA_TX_MTU_MAX;
+
+	/* Set MTU */
+	val = mvreg_read(pp, MVNETA_TX_MTU);
+	val &= ~MVNETA_TX_MTU_MAX;
+	val |= mtu;
+	mvreg_write(pp, MVNETA_TX_MTU, val);
+
+	/* TX token size and all TXQs token size must be larger that MTU */
+	val = mvreg_read(pp, MVNETA_TX_TOKEN_SIZE);
+
+	size = val & MVNETA_TX_TOKEN_SIZE_MAX;
+	if (size < mtu) {
+		size = mtu;
+		val &= ~MVNETA_TX_TOKEN_SIZE_MAX;
+		val |= size;
+		mvreg_write(pp, MVNETA_TX_TOKEN_SIZE, val);
+	}
+	for (queue = 0; queue < txq_number; queue++) {
+		val = mvreg_read(pp, MVNETA_TXQ_TOKEN_SIZE_REG(queue));
+
+		size = val & MVNETA_TXQ_TOKEN_SIZE_MAX;
+		if (size < mtu) {
+			size = mtu;
+			val &= ~MVNETA_TXQ_TOKEN_SIZE_MAX;
+			val |= size;
+			mvreg_write(pp, MVNETA_TXQ_TOKEN_SIZE_REG(queue), val);
+		}
+	}
+}
+
+/* Set unicast address */
+static void mvneta_set_ucast_addr(struct mvneta_port *pp, u8 last_nibble,
+				  int queue)
+{
+	unsigned int unicast_reg;
+	unsigned int tbl_offset;
+	unsigned int reg_offset;
+
+	/* Locate the Unicast table entry */
+	last_nibble = (0xf & last_nibble);
+
+	/* offset from unicast tbl base */
+	tbl_offset = (last_nibble / 4) * 4;
+
+	/* offset within the above reg  */
+	reg_offset = last_nibble % 4;
+
+	unicast_reg = mvreg_read(pp, (MVNETA_DA_FILT_UCAST_BASE + tbl_offset));
+
+	if (queue == -1) {
+		/* Clear accepts frame bit at specified unicast DA tbl entry */
+		unicast_reg &= ~(0xff << (8 * reg_offset));
+	} else {
+		unicast_reg &= ~(0xff << (8 * reg_offset));
+		unicast_reg |= ((0x01 | (queue << 1)) << (8 * reg_offset));
+	}
+
+	mvreg_write(pp, (MVNETA_DA_FILT_UCAST_BASE + tbl_offset), unicast_reg);
+}
+
+/* Set mac address */
+static void mvneta_mac_addr_set(struct mvneta_port *pp, unsigned char *addr,
+				int queue)
+{
+	unsigned int mac_h;
+	unsigned int mac_l;
+
+	if (queue != -1) {
+		mac_l = (addr[4] << 8) | (addr[5]);
+		mac_h = (addr[0] << 24) | (addr[1] << 16) |
+			(addr[2] << 8) | (addr[3] << 0);
+
+		mvreg_write(pp, MVNETA_MAC_ADDR_LOW, mac_l);
+		mvreg_write(pp, MVNETA_MAC_ADDR_HIGH, mac_h);
+	}
+
+	/* Accept frames of this address */
+	mvneta_set_ucast_addr(pp, addr[5], queue);
+}
+
+/* Set the number of packets that will be received before RX interrupt
+ * will be generated by HW.
+ */
+static void mvneta_rx_pkts_coal_set(struct mvneta_port *pp,
+				    struct mvneta_rx_queue *rxq, u32 value)
+{
+	mvreg_write(pp, MVNETA_RXQ_THRESHOLD_REG(rxq->id),
+		    value | MVNETA_RXQ_NON_OCCUPIED(0));
+	rxq->pkts_coal = value;
+}
+
+/* Set the time delay in usec before RX interrupt will be generated by
+ * HW.
+ */
+static void mvneta_rx_time_coal_set(struct mvneta_port *pp,
+				    struct mvneta_rx_queue *rxq, u32 value)
+{
+	u32 val;
+	unsigned long clk_rate;
+
+	clk_rate = clk_get_rate(pp->clk);
+	val = (clk_rate / 1000000) * value;
+
+	mvreg_write(pp, MVNETA_RXQ_TIME_COAL_REG(rxq->id), val);
+	rxq->time_coal = value;
+}
+
+/* Set threshold for TX_DONE pkts coalescing */
+static void mvneta_tx_done_pkts_coal_set(struct mvneta_port *pp,
+					 struct mvneta_tx_queue *txq, u32 value)
+{
+	u32 val;
+
+	val = mvreg_read(pp, MVNETA_TXQ_SIZE_REG(txq->id));
+
+	val &= ~MVNETA_TXQ_SENT_THRESH_ALL_MASK;
+	val |= MVNETA_TXQ_SENT_THRESH_MASK(value);
+
+	mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), val);
+
+	txq->done_pkts_coal = value;
+}
+
+/* Trigger tx done timer in MVNETA_TX_DONE_TIMER_PERIOD msecs */
+static void mvneta_add_tx_done_timer(struct mvneta_port *pp)
+{
+	if (test_and_set_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags) == 0) {
+		pp->tx_done_timer.expires = jiffies +
+			msecs_to_jiffies(MVNETA_TX_DONE_TIMER_PERIOD);
+		add_timer(&pp->tx_done_timer);
+	}
+}
+
+
+/* Handle rx descriptor fill by setting buf_cookie and buf_phys_addr */
+static void mvneta_rx_desc_fill(struct mvneta_rx_desc *rx_desc,
+				u32 phys_addr, u32 cookie)
+{
+	rx_desc->buf_cookie = cookie;
+	rx_desc->buf_phys_addr = phys_addr;
+}
+
+/* Decrement sent descriptors counter */
+static void mvneta_txq_sent_desc_dec(struct mvneta_port *pp,
+				     struct mvneta_tx_queue *txq,
+				     int sent_desc)
+{
+	u32 val;
+
+	/* Only 255 TX descriptors can be updated at once */
+	while (sent_desc > 0xff) {
+		val = 0xff << MVNETA_TXQ_DEC_SENT_SHIFT;
+		mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
+		sent_desc = sent_desc - 0xff;
+	}
+
+	val = sent_desc << MVNETA_TXQ_DEC_SENT_SHIFT;
+	mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
+}
+
+/* Get number of TX descriptors already sent by HW */
+static int mvneta_txq_sent_desc_num_get(struct mvneta_port *pp,
+					struct mvneta_tx_queue *txq)
+{
+	u32 val;
+	int sent_desc;
+
+	val = mvreg_read(pp, MVNETA_TXQ_STATUS_REG(txq->id));
+	sent_desc = (val & MVNETA_TXQ_SENT_DESC_MASK) >>
+		MVNETA_TXQ_SENT_DESC_SHIFT;
+
+	return sent_desc;
+}
+
+/* Get number of sent descriptors and decrement counter.
+ *  The number of sent descriptors is returned.
+ */
+static int mvneta_txq_sent_desc_proc(struct mvneta_port *pp,
+				     struct mvneta_tx_queue *txq)
+{
+	int sent_desc;
+
+	/* Get number of sent descriptors */
+	sent_desc = mvneta_txq_sent_desc_num_get(pp, txq);
+
+	/* Decrement sent descriptors counter */
+	if (sent_desc)
+		mvneta_txq_sent_desc_dec(pp, txq, sent_desc);
+
+	return sent_desc;
+}
+
+/* Set TXQ descriptors fields relevant for CSUM calculation */
+static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
+				int ip_hdr_len, int l4_proto)
+{
+	u32 command;
+
+	/* Fields: L3_offset, IP_hdrlen, L3_type, G_IPv4_chk,
+	 * G_L4_chk, L4_type; required only for checksum
+	 * calculation
+	 */
+	command =  l3_offs    << MVNETA_TX_L3_OFF_SHIFT;
+	command |= ip_hdr_len << MVNETA_TX_IP_HLEN_SHIFT;
+
+	if (l3_proto == swab16(ETH_P_IP))
+		command |= MVNETA_TXD_IP_CSUM;
+	else
+		command |= MVNETA_TX_L3_IP6;
+
+	if (l4_proto == IPPROTO_TCP)
+		command |=  MVNETA_TX_L4_CSUM_FULL;
+	else if (l4_proto == IPPROTO_UDP)
+		command |= MVNETA_TX_L4_UDP | MVNETA_TX_L4_CSUM_FULL;
+	else
+		command |= MVNETA_TX_L4_CSUM_NOT;
+
+	return command;
+}
+
+
+/* Display more error info */
+static void mvneta_rx_error(struct mvneta_port *pp,
+			    struct mvneta_rx_desc *rx_desc)
+{
+	u32 status = rx_desc->status;
+
+	if (!mvneta_rxq_desc_is_first_last(rx_desc)) {
+		netdev_err(pp->dev,
+			   "bad rx status %08x (buffer oversize), size=%d\n",
+			   rx_desc->status, rx_desc->data_size);
+		return;
+	}
+
+	switch (status & MVNETA_RXD_ERR_CODE_MASK) {
+	case MVNETA_RXD_ERR_CRC:
+		netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n",
+			   status, rx_desc->data_size);
+		break;
+	case MVNETA_RXD_ERR_OVERRUN:
+		netdev_err(pp->dev, "bad rx status %08x (overrun error), size=%d\n",
+			   status, rx_desc->data_size);
+		break;
+	case MVNETA_RXD_ERR_LEN:
+		netdev_err(pp->dev, "bad rx status %08x (max frame length error), size=%d\n",
+			   status, rx_desc->data_size);
+		break;
+	case MVNETA_RXD_ERR_RESOURCE:
+		netdev_err(pp->dev, "bad rx status %08x (resource error), size=%d\n",
+			   status, rx_desc->data_size);
+		break;
+	}
+}
+
+/* Handle RX checksum offload */
+static void mvneta_rx_csum(struct mvneta_port *pp,
+			   struct mvneta_rx_desc *rx_desc,
+			   struct sk_buff *skb)
+{
+	if ((rx_desc->status & MVNETA_RXD_L3_IP4) &&
+	    (rx_desc->status & MVNETA_RXD_L4_CSUM_OK)) {
+		skb->csum = 0;
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		return;
+	}
+
+	skb->ip_summed = CHECKSUM_NONE;
+}
+
+/* Return tx queue pointer (find last set bit) according to causeTxDone reg */
+static struct mvneta_tx_queue *mvneta_tx_done_policy(struct mvneta_port *pp,
+						     u32 cause)
+{
+	int queue = fls(cause) - 1;
+
+	return (queue < 0 || queue >= txq_number) ? NULL : &pp->txqs[queue];
+}
+
+/* Free tx queue skbuffs */
+static void mvneta_txq_bufs_free(struct mvneta_port *pp,
+				 struct mvneta_tx_queue *txq, int num)
+{
+	int i;
+
+	for (i = 0; i < num; i++) {
+		struct mvneta_tx_desc *tx_desc = txq->descs +
+			txq->txq_get_index;
+		struct sk_buff *skb = txq->tx_skb[txq->txq_get_index];
+
+		mvneta_txq_inc_get(txq);
+
+		if (!skb)
+			continue;
+
+		dma_unmap_single(pp->dev->dev.parent, tx_desc->buf_phys_addr,
+				 tx_desc->data_size, DMA_TO_DEVICE);
+		dev_kfree_skb_any(skb);
+	}
+}
+
+/* Handle end of transmission */
+static int mvneta_txq_done(struct mvneta_port *pp,
+			   struct mvneta_tx_queue *txq)
+{
+	struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
+	int tx_done;
+
+	tx_done = mvneta_txq_sent_desc_proc(pp, txq);
+	if (tx_done == 0)
+		return tx_done;
+	mvneta_txq_bufs_free(pp, txq, tx_done);
+
+	txq->count -= tx_done;
+
+	if (netif_tx_queue_stopped(nq)) {
+		if (txq->size - txq->count >= MAX_SKB_FRAGS + 1)
+			netif_tx_wake_queue(nq);
+	}
+
+	return tx_done;
+}
+
+/* Refill processing */
+static int mvneta_rx_refill(struct mvneta_port *pp,
+			    struct mvneta_rx_desc *rx_desc)
+
+{
+	dma_addr_t phys_addr;
+	struct sk_buff *skb;
+
+	skb = netdev_alloc_skb(pp->dev, pp->pkt_size);
+	if (!skb)
+		return -ENOMEM;
+
+	phys_addr = dma_map_single(pp->dev->dev.parent, skb->head,
+				   MVNETA_RX_BUF_SIZE(pp->pkt_size),
+				   DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(pp->dev->dev.parent, phys_addr))) {
+		dev_kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	mvneta_rx_desc_fill(rx_desc, phys_addr, (u32)skb);
+
+	return 0;
+}
+
+/* Handle tx checksum */
+static u32 mvneta_skb_tx_csum(struct mvneta_port *pp, struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		int ip_hdr_len = 0;
+		u8 l4_proto;
+
+		if (skb->protocol == htons(ETH_P_IP)) {
+			struct iphdr *ip4h = ip_hdr(skb);
+
+			/* Calculate IPv4 checksum and L4 checksum */
+			ip_hdr_len = ip4h->ihl;
+			l4_proto = ip4h->protocol;
+		} else if (skb->protocol == htons(ETH_P_IPV6)) {
+			struct ipv6hdr *ip6h = ipv6_hdr(skb);
+
+			/* Read l4_protocol from one of IPv6 extra headers */
+			if (skb_network_header_len(skb) > 0)
+				ip_hdr_len = (skb_network_header_len(skb) >> 2);
+			l4_proto = ip6h->nexthdr;
+		} else
+			return MVNETA_TX_L4_CSUM_NOT;
+
+		return mvneta_txq_desc_csum(skb_network_offset(skb),
+				skb->protocol, ip_hdr_len, l4_proto);
+	}
+
+	return MVNETA_TX_L4_CSUM_NOT;
+}
+
+/* Returns rx queue pointer (find last set bit) according to causeRxTx
+ * value
+ */
+static struct mvneta_rx_queue *mvneta_rx_policy(struct mvneta_port *pp,
+						u32 cause)
+{
+	int queue = fls(cause >> 8) - 1;
+
+	return (queue < 0 || queue >= rxq_number) ? NULL : &pp->rxqs[queue];
+}
+
+/* Drop packets received by the RXQ and free buffers */
+static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
+				 struct mvneta_rx_queue *rxq)
+{
+	int rx_done, i;
+
+	rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
+	for (i = 0; i < rxq->size; i++) {
+		struct mvneta_rx_desc *rx_desc = rxq->descs + i;
+		struct sk_buff *skb = (struct sk_buff *)rx_desc->buf_cookie;
+
+		dev_kfree_skb_any(skb);
+		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
+				 rx_desc->data_size, DMA_FROM_DEVICE);
+	}
+
+	if (rx_done)
+		mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);
+}
+
+/* Main rx processing */
+static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
+		     struct mvneta_rx_queue *rxq)
+{
+	struct net_device *dev = pp->dev;
+	int rx_done, rx_filled;
+
+	/* Get number of received packets */
+	rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
+
+	if (rx_todo > rx_done)
+		rx_todo = rx_done;
+
+	rx_done = 0;
+	rx_filled = 0;
+
+	/* Fairness NAPI loop */
+	while (rx_done < rx_todo) {
+		struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
+		struct sk_buff *skb;
+		u32 rx_status;
+		int rx_bytes, err;
+
+		prefetch(rx_desc);
+		rx_done++;
+		rx_filled++;
+		rx_status = rx_desc->status;
+		skb = (struct sk_buff *)rx_desc->buf_cookie;
+
+		if (!mvneta_rxq_desc_is_first_last(rx_desc) ||
+		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
+			dev->stats.rx_errors++;
+			mvneta_rx_error(pp, rx_desc);
+			mvneta_rx_desc_fill(rx_desc, rx_desc->buf_phys_addr,
+					    (u32)skb);
+			continue;
+		}
+
+		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
+				 rx_desc->data_size, DMA_FROM_DEVICE);
+
+		rx_bytes = rx_desc->data_size -
+			(ETH_FCS_LEN + MVNETA_MH_SIZE);
+		u64_stats_update_begin(&pp->rx_stats.syncp);
+		pp->rx_stats.packets++;
+		pp->rx_stats.bytes += rx_bytes;
+		u64_stats_update_end(&pp->rx_stats.syncp);
+
+		/* Linux processing */
+		skb_reserve(skb, MVNETA_MH_SIZE);
+		skb_put(skb, rx_bytes);
+
+		skb->protocol = eth_type_trans(skb, dev);
+
+		mvneta_rx_csum(pp, rx_desc, skb);
+
+		napi_gro_receive(&pp->napi, skb);
+
+		/* Refill processing */
+		err = mvneta_rx_refill(pp, rx_desc);
+		if (err) {
+			netdev_err(pp->dev, "Linux processing - Can't refill\n");
+			rxq->missed++;
+			rx_filled--;
+		}
+	}
+
+	/* Update rxq management counters */
+	mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_filled);
+
+	return rx_done;
+}
+
+/* Handle tx fragmentation processing */
+static int mvneta_tx_frag_process(struct mvneta_port *pp, struct sk_buff *skb,
+				  struct mvneta_tx_queue *txq)
+{
+	struct mvneta_tx_desc *tx_desc;
+	int i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		void *addr = page_address(frag->page.p) + frag->page_offset;
+
+		tx_desc = mvneta_txq_next_desc_get(txq);
+		tx_desc->data_size = frag->size;
+
+		tx_desc->buf_phys_addr =
+			dma_map_single(pp->dev->dev.parent, addr,
+				       tx_desc->data_size, DMA_TO_DEVICE);
+
+		if (dma_mapping_error(pp->dev->dev.parent,
+				      tx_desc->buf_phys_addr)) {
+			mvneta_txq_desc_put(txq);
+			goto error;
+		}
+
+		if (i == (skb_shinfo(skb)->nr_frags - 1)) {
+			/* Last descriptor */
+			tx_desc->command = MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD;
+
+			txq->tx_skb[txq->txq_put_index] = skb;
+
+			mvneta_txq_inc_put(txq);
+		} else {
+			/* Descriptor in the middle: Not First, Not Last */
+			tx_desc->command = 0;
+
+			txq->tx_skb[txq->txq_put_index] = NULL;
+			mvneta_txq_inc_put(txq);
+		}
+	}
+
+	return 0;
+
+error:
+	/* Release all descriptors that were used to map fragments of
+	 * this packet, as well as the corresponding DMA mappings
+	 */
+	for (i = i - 1; i >= 0; i--) {
+		tx_desc = txq->descs + i;
+		dma_unmap_single(pp->dev->dev.parent,
+				 tx_desc->buf_phys_addr,
+				 tx_desc->data_size,
+				 DMA_TO_DEVICE);
+		mvneta_txq_desc_put(txq);
+	}
+
+	return -ENOMEM;
+}
+
+/* Main tx processing */
+static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+	struct mvneta_tx_queue *txq = &pp->txqs[txq_def];
+	struct mvneta_tx_desc *tx_desc;
+	struct netdev_queue *nq;
+	int frags = 0;
+	u32 tx_cmd;
+
+	if (!netif_running(dev))
+		goto out;
+
+	frags = skb_shinfo(skb)->nr_frags + 1;
+	nq    = netdev_get_tx_queue(dev, txq_def);
+
+	/* Get a descriptor for the first part of the packet */
+	tx_desc = mvneta_txq_next_desc_get(txq);
+
+	tx_cmd = mvneta_skb_tx_csum(pp, skb);
+
+	tx_desc->data_size = skb_headlen(skb);
+
+	tx_desc->buf_phys_addr = dma_map_single(dev->dev.parent, skb->data,
+						tx_desc->data_size,
+						DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev->dev.parent,
+				       tx_desc->buf_phys_addr))) {
+		mvneta_txq_desc_put(txq);
+		frags = 0;
+		goto out;
+	}
+
+	if (frags == 1) {
+		/* First and Last descriptor */
+		tx_cmd |= MVNETA_TXD_FLZ_DESC;
+		tx_desc->command = tx_cmd;
+		txq->tx_skb[txq->txq_put_index] = skb;
+		mvneta_txq_inc_put(txq);
+	} else {
+		/* First but not Last */
+		tx_cmd |= MVNETA_TXD_F_DESC;
+		txq->tx_skb[txq->txq_put_index] = NULL;
+		mvneta_txq_inc_put(txq);
+		tx_desc->command = tx_cmd;
+		/* Continue with other skb fragments */
+		if (mvneta_tx_frag_process(pp, skb, txq)) {
+			dma_unmap_single(dev->dev.parent,
+					 tx_desc->buf_phys_addr,
+					 tx_desc->data_size,
+					 DMA_TO_DEVICE);
+			mvneta_txq_desc_put(txq);
+			frags = 0;
+			goto out;
+		}
+	}
+
+	txq->count += frags;
+	mvneta_txq_pend_desc_add(pp, txq, frags);
+
+	if (txq->size - txq->count < MAX_SKB_FRAGS + 1)
+		netif_tx_stop_queue(nq);
+
+out:
+	if (frags > 0) {
+		u64_stats_update_begin(&pp->tx_stats.syncp);
+		pp->tx_stats.packets++;
+		pp->tx_stats.bytes += skb->len;
+		u64_stats_update_end(&pp->tx_stats.syncp);
+
+	} else {
+		dev->stats.tx_dropped++;
+		dev_kfree_skb_any(skb);
+	}
+
+	if (txq->count >= MVNETA_TXDONE_COAL_PKTS)
+		mvneta_txq_done(pp, txq);
+
+	/* If after calling mvneta_txq_done, count equals
+	 * frags, we need to set the timer
+	 */
+	if (txq->count == frags && frags > 0)
+		mvneta_add_tx_done_timer(pp);
+
+	return NETDEV_TX_OK;
+}
+
+
+/* Free tx resources, when resetting a port */
+static void mvneta_txq_done_force(struct mvneta_port *pp,
+				  struct mvneta_tx_queue *txq)
+
+{
+	int tx_done = txq->count;
+
+	mvneta_txq_bufs_free(pp, txq, tx_done);
+
+	/* reset txq */
+	txq->count = 0;
+	txq->txq_put_index = 0;
+	txq->txq_get_index = 0;
+}
+
+/* handle tx done - called from tx done timer callback */
+static u32 mvneta_tx_done_gbe(struct mvneta_port *pp, u32 cause_tx_done,
+			      int *tx_todo)
+{
+	struct mvneta_tx_queue *txq;
+	u32 tx_done = 0;
+	struct netdev_queue *nq;
+
+	*tx_todo = 0;
+	while (cause_tx_done != 0) {
+		txq = mvneta_tx_done_policy(pp, cause_tx_done);
+		if (!txq)
+			break;
+
+		nq = netdev_get_tx_queue(pp->dev, txq->id);
+		__netif_tx_lock(nq, smp_processor_id());
+
+		if (txq->count) {
+			tx_done += mvneta_txq_done(pp, txq);
+			*tx_todo += txq->count;
+		}
+
+		__netif_tx_unlock(nq);
+		cause_tx_done &= ~((1 << txq->id));
+	}
+
+	return tx_done;
+}
+
+/* Compute crc8 of the specified address, using a unique algorithm ,
+ * according to hw spec, different than generic crc8 algorithm
+ */
+static int mvneta_addr_crc(unsigned char *addr)
+{
+	int crc = 0;
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		int j;
+
+		crc = (crc ^ addr[i]) << 8;
+		for (j = 7; j >= 0; j--) {
+			if (crc & (0x100 << j))
+				crc ^= 0x107 << j;
+		}
+	}
+
+	return crc;
+}
+
+/* This method controls the net device special MAC multicast support.
+ * The Special Multicast Table for MAC addresses supports MAC of the form
+ * 0x01-00-5E-00-00-XX (where XX is between 0x00 and 0xFF).
+ * The MAC DA[7:0] bits are used as a pointer to the Special Multicast
+ * Table entries in the DA-Filter table. This method set the Special
+ * Multicast Table appropriate entry.
+ */
+static void mvneta_set_special_mcast_addr(struct mvneta_port *pp,
+					  unsigned char last_byte,
+					  int queue)
+{
+	unsigned int smc_table_reg;
+	unsigned int tbl_offset;
+	unsigned int reg_offset;
+
+	/* Register offset from SMC table base    */
+	tbl_offset = (last_byte / 4);
+	/* Entry offset within the above reg */
+	reg_offset = last_byte % 4;
+
+	smc_table_reg = mvreg_read(pp, (MVNETA_DA_FILT_SPEC_MCAST
+					+ tbl_offset * 4));
+
+	if (queue == -1)
+		smc_table_reg &= ~(0xff << (8 * reg_offset));
+	else {
+		smc_table_reg &= ~(0xff << (8 * reg_offset));
+		smc_table_reg |= ((0x01 | (queue << 1)) << (8 * reg_offset));
+	}
+
+	mvreg_write(pp, MVNETA_DA_FILT_SPEC_MCAST + tbl_offset * 4,
+		    smc_table_reg);
+}
+
+/* This method controls the network device Other MAC multicast support.
+ * The Other Multicast Table is used for multicast of another type.
+ * A CRC-8 is used as an index to the Other Multicast Table entries
+ * in the DA-Filter table.
+ * The method gets the CRC-8 value from the calling routine and
+ * sets the Other Multicast Table appropriate entry according to the
+ * specified CRC-8 .
+ */
+static void mvneta_set_other_mcast_addr(struct mvneta_port *pp,
+					unsigned char crc8,
+					int queue)
+{
+	unsigned int omc_table_reg;
+	unsigned int tbl_offset;
+	unsigned int reg_offset;
+
+	tbl_offset = (crc8 / 4) * 4; /* Register offset from OMC table base */
+	reg_offset = crc8 % 4;	     /* Entry offset within the above reg   */
+
+	omc_table_reg = mvreg_read(pp, MVNETA_DA_FILT_OTH_MCAST + tbl_offset);
+
+	if (queue == -1) {
+		/* Clear accepts frame bit at specified Other DA table entry */
+		omc_table_reg &= ~(0xff << (8 * reg_offset));
+	} else {
+		omc_table_reg &= ~(0xff << (8 * reg_offset));
+		omc_table_reg |= ((0x01 | (queue << 1)) << (8 * reg_offset));
+	}
+
+	mvreg_write(pp, MVNETA_DA_FILT_OTH_MCAST + tbl_offset, omc_table_reg);
+}
+
+/* The network device supports multicast using two tables:
+ *    1) Special Multicast Table for MAC addresses of the form
+ *       0x01-00-5E-00-00-XX (where XX is between 0x00 and 0xFF).
+ *       The MAC DA[7:0] bits are used as a pointer to the Special Multicast
+ *       Table entries in the DA-Filter table.
+ *    2) Other Multicast Table for multicast of another type. A CRC-8 value
+ *       is used as an index to the Other Multicast Table entries in the
+ *       DA-Filter table.
+ */
+static int mvneta_mcast_addr_set(struct mvneta_port *pp, unsigned char *p_addr,
+				 int queue)
+{
+	unsigned char crc_result = 0;
+
+	if (memcmp(p_addr, "\x01\x00\x5e\x00\x00", 5) == 0) {
+		mvneta_set_special_mcast_addr(pp, p_addr[5], queue);
+		return 0;
+	}
+
+	crc_result = mvneta_addr_crc(p_addr);
+	if (queue == -1) {
+		if (pp->mcast_count[crc_result] == 0) {
+			netdev_info(pp->dev, "No valid Mcast for crc8=0x%02x\n",
+				    crc_result);
+			return -EINVAL;
+		}
+
+		pp->mcast_count[crc_result]--;
+		if (pp->mcast_count[crc_result] != 0) {
+			netdev_info(pp->dev,
+				    "After delete there are %d valid Mcast for crc8=0x%02x\n",
+				    pp->mcast_count[crc_result], crc_result);
+			return -EINVAL;
+		}
+	} else
+		pp->mcast_count[crc_result]++;
+
+	mvneta_set_other_mcast_addr(pp, crc_result, queue);
+
+	return 0;
+}
+
+/* Configure Fitering mode of Ethernet port */
+static void mvneta_rx_unicast_promisc_set(struct mvneta_port *pp,
+					  int is_promisc)
+{
+	u32 port_cfg_reg, val;
+
+	port_cfg_reg = mvreg_read(pp, MVNETA_PORT_CONFIG);
+
+	val = mvreg_read(pp, MVNETA_TYPE_PRIO);
+
+	/* Set / Clear UPM bit in port configuration register */
+	if (is_promisc) {
+		/* Accept all Unicast addresses */
+		port_cfg_reg |= MVNETA_UNI_PROMISC_MODE;
+		val |= MVNETA_FORCE_UNI;
+		mvreg_write(pp, MVNETA_MAC_ADDR_LOW, 0xffff);
+		mvreg_write(pp, MVNETA_MAC_ADDR_HIGH, 0xffffffff);
+	} else {
+		/* Reject all Unicast addresses */
+		port_cfg_reg &= ~MVNETA_UNI_PROMISC_MODE;
+		val &= ~MVNETA_FORCE_UNI;
+	}
+
+	mvreg_write(pp, MVNETA_PORT_CONFIG, port_cfg_reg);
+	mvreg_write(pp, MVNETA_TYPE_PRIO, val);
+}
+
+/* register unicast and multicast addresses */
+static void mvneta_set_rx_mode(struct net_device *dev)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+	struct netdev_hw_addr *ha;
+
+	if (dev->flags & IFF_PROMISC) {
+		/* Accept all: Multicast + Unicast */
+		mvneta_rx_unicast_promisc_set(pp, 1);
+		mvneta_set_ucast_table(pp, rxq_def);
+		mvneta_set_special_mcast_table(pp, rxq_def);
+		mvneta_set_other_mcast_table(pp, rxq_def);
+	} else {
+		/* Accept single Unicast */
+		mvneta_rx_unicast_promisc_set(pp, 0);
+		mvneta_set_ucast_table(pp, -1);
+		mvneta_mac_addr_set(pp, dev->dev_addr, rxq_def);
+
+		if (dev->flags & IFF_ALLMULTI) {
+			/* Accept all multicast */
+			mvneta_set_special_mcast_table(pp, rxq_def);
+			mvneta_set_other_mcast_table(pp, rxq_def);
+		} else {
+			/* Accept only initialized multicast */
+			mvneta_set_special_mcast_table(pp, -1);
+			mvneta_set_other_mcast_table(pp, -1);
+
+			if (!netdev_mc_empty(dev)) {
+				netdev_for_each_mc_addr(ha, dev) {
+					mvneta_mcast_addr_set(pp, ha->addr,
+							      rxq_def);
+				}
+			}
+		}
+	}
+}
+
+/* Interrupt handling - the callback for request_irq() */
+static irqreturn_t mvneta_isr(int irq, void *dev_id)
+{
+	struct mvneta_port *pp = (struct mvneta_port *)dev_id;
+
+	/* Mask all interrupts */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+
+	napi_schedule(&pp->napi);
+
+	return IRQ_HANDLED;
+}
+
+/* NAPI handler
+ * Bits 0 - 7 of the causeRxTx register indicate that are transmitted
+ * packets on the corresponding TXQ (Bit 0 is for TX queue 1).
+ * Bits 8 -15 of the cause Rx Tx register indicate that are received
+ * packets on the corresponding RXQ (Bit 8 is for RX queue 0).
+ * Each CPU has its own causeRxTx register
+ */
+static int mvneta_poll(struct napi_struct *napi, int budget)
+{
+	int rx_done = 0;
+	u32 cause_rx_tx;
+	unsigned long flags;
+	struct mvneta_port *pp = netdev_priv(napi->dev);
+
+	if (!netif_running(pp->dev)) {
+		napi_complete(napi);
+		return rx_done;
+	}
+
+	/* Read cause register */
+	cause_rx_tx = mvreg_read(pp, MVNETA_INTR_NEW_CAUSE) &
+		MVNETA_RX_INTR_MASK(rxq_number);
+
+	/* For the case where the last mvneta_poll did not process all
+	 * RX packets
+	 */
+	cause_rx_tx |= pp->cause_rx_tx;
+	if (rxq_number > 1) {
+		while ((cause_rx_tx != 0) && (budget > 0)) {
+			int count;
+			struct mvneta_rx_queue *rxq;
+			/* get rx queue number from cause_rx_tx */
+			rxq = mvneta_rx_policy(pp, cause_rx_tx);
+			if (!rxq)
+				break;
+
+			/* process the packet in that rx queue */
+			count = mvneta_rx(pp, budget, rxq);
+			rx_done += count;
+			budget -= count;
+			if (budget > 0) {
+				/* set off the rx bit of the
+				 * corresponding bit in the cause rx
+				 * tx register, so that next iteration
+				 * will find the next rx queue where
+				 * packets are received on
+				 */
+				cause_rx_tx &= ~((1 << rxq->id) << 8);
+			}
+		}
+	} else {
+		rx_done = mvneta_rx(pp, budget, &pp->rxqs[rxq_def]);
+		budget -= rx_done;
+	}
+
+	if (budget > 0) {
+		cause_rx_tx = 0;
+		napi_complete(napi);
+		local_irq_save(flags);
+		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+			    MVNETA_RX_INTR_MASK(rxq_number));
+		local_irq_restore(flags);
+	}
+
+	pp->cause_rx_tx = cause_rx_tx;
+	return rx_done;
+}
+
+/* tx done timer callback */
+static void mvneta_tx_done_timer_callback(unsigned long data)
+{
+	struct net_device *dev = (struct net_device *)data;
+	struct mvneta_port *pp = netdev_priv(dev);
+	int tx_done = 0, tx_todo = 0;
+
+	if (!netif_running(dev))
+		return ;
+
+	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
+
+	tx_done = mvneta_tx_done_gbe(pp,
+				     (((1 << txq_number) - 1) &
+				      MVNETA_CAUSE_TXQ_SENT_DESC_ALL_MASK),
+				     &tx_todo);
+	if (tx_todo > 0)
+		mvneta_add_tx_done_timer(pp);
+}
+
+/* Handle rxq fill: allocates rxq skbs; called when initializing a port */
+static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
+			   int num)
+{
+	struct net_device *dev = pp->dev;
+	int i;
+
+	for (i = 0; i < num; i++) {
+		struct sk_buff *skb;
+		struct mvneta_rx_desc *rx_desc;
+		unsigned long phys_addr;
+
+		skb = dev_alloc_skb(pp->pkt_size);
+		if (!skb) {
+			netdev_err(dev, "%s:rxq %d, %d of %d buffs  filled\n",
+				__func__, rxq->id, i, num);
+			break;
+		}
+
+		rx_desc = rxq->descs + i;
+		memset(rx_desc, 0, sizeof(struct mvneta_rx_desc));
+		phys_addr = dma_map_single(dev->dev.parent, skb->head,
+					   MVNETA_RX_BUF_SIZE(pp->pkt_size),
+					   DMA_FROM_DEVICE);
+		if (unlikely(dma_mapping_error(dev->dev.parent, phys_addr))) {
+			dev_kfree_skb(skb);
+			break;
+		}
+
+		mvneta_rx_desc_fill(rx_desc, phys_addr, (u32)skb);
+	}
+
+	/* Add this number of RX descriptors as non occupied (ready to
+	 * get packets)
+	 */
+	mvneta_rxq_non_occup_desc_add(pp, rxq, i);
+
+	return i;
+}
+
+/* Free all packets pending transmit from all TXQs and reset TX port */
+static void mvneta_tx_reset(struct mvneta_port *pp)
+{
+	int queue;
+
+	/* free the skb's in the hal tx ring */
+	for (queue = 0; queue < txq_number; queue++)
+		mvneta_txq_done_force(pp, &pp->txqs[queue]);
+
+	mvreg_write(pp, MVNETA_PORT_TX_RESET, MVNETA_PORT_TX_DMA_RESET);
+	mvreg_write(pp, MVNETA_PORT_TX_RESET, 0);
+}
+
+static void mvneta_rx_reset(struct mvneta_port *pp)
+{
+	mvreg_write(pp, MVNETA_PORT_RX_RESET, MVNETA_PORT_RX_DMA_RESET);
+	mvreg_write(pp, MVNETA_PORT_RX_RESET, 0);
+}
+
+/* Rx/Tx queue initialization/cleanup methods */
+
+/* Create a specified RX queue */
+static int mvneta_rxq_init(struct mvneta_port *pp,
+			   struct mvneta_rx_queue *rxq)
+
+{
+	rxq->size = pp->rx_ring_size;
+
+	/* Allocate memory for RX descriptors */
+	rxq->descs = dma_alloc_coherent(pp->dev->dev.parent,
+					rxq->size * MVNETA_DESC_ALIGNED_SIZE,
+					&rxq->descs_phys, GFP_KERNEL);
+	if (rxq->descs == NULL) {
+		netdev_err(pp->dev,
+			   "rxq=%d: Can't allocate %d bytes for %d RX descr\n",
+			   rxq->id, rxq->size * MVNETA_DESC_ALIGNED_SIZE,
+			   rxq->size);
+		return -ENOMEM;
+	}
+
+	BUG_ON(rxq->descs !=
+	       PTR_ALIGN(rxq->descs, MVNETA_CPU_D_CACHE_LINE_SIZE));
+
+	rxq->last_desc = rxq->size - 1;
+
+	/* Set Rx descriptors queue starting address */
+	mvreg_write(pp, MVNETA_RXQ_BASE_ADDR_REG(rxq->id), rxq->descs_phys);
+	mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), rxq->size);
+
+	/* Set Offset */
+	mvneta_rxq_offset_set(pp, rxq, NET_SKB_PAD);
+
+	/* Set coalescing pkts and time */
+	mvneta_rx_pkts_coal_set(pp, rxq, rxq->pkts_coal);
+	mvneta_rx_time_coal_set(pp, rxq, rxq->time_coal);
+
+	/* Fill RXQ with buffers from RX pool */
+	mvneta_rxq_buf_size_set(pp, rxq, MVNETA_RX_BUF_SIZE(pp->pkt_size));
+	mvneta_rxq_bm_disable(pp, rxq);
+	mvneta_rxq_fill(pp, rxq, rxq->size);
+
+	return 0;
+}
+
+/* Cleanup Rx queue */
+static void mvneta_rxq_deinit(struct mvneta_port *pp,
+			      struct mvneta_rx_queue *rxq)
+{
+	mvneta_rxq_drop_pkts(pp, rxq);
+
+	if (rxq->descs)
+		dma_free_coherent(pp->dev->dev.parent,
+				  rxq->size * MVNETA_DESC_ALIGNED_SIZE,
+				  rxq->descs,
+				  rxq->descs_phys);
+
+	rxq->descs             = NULL;
+	rxq->last_desc         = 0;
+	rxq->next_desc_to_proc = 0;
+	rxq->descs_phys        = 0;
+}
+
+/* Create and initialize a tx queue */
+static int mvneta_txq_init(struct mvneta_port *pp,
+			   struct mvneta_tx_queue *txq)
+{
+	txq->size = pp->tx_ring_size;
+
+	/* Allocate memory for TX descriptors */
+	txq->descs = dma_alloc_coherent(pp->dev->dev.parent,
+					txq->size * MVNETA_DESC_ALIGNED_SIZE,
+					&txq->descs_phys, GFP_KERNEL);
+	if (txq->descs == NULL) {
+		netdev_err(pp->dev,
+			   "txQ=%d: Can't allocate %d bytes for %d TX descr\n",
+			   txq->id, txq->size * MVNETA_DESC_ALIGNED_SIZE,
+			   txq->size);
+		return -ENOMEM;
+	}
+
+	/* Make sure descriptor address is cache line size aligned  */
+	BUG_ON(txq->descs !=
+	       PTR_ALIGN(txq->descs, MVNETA_CPU_D_CACHE_LINE_SIZE));
+
+	txq->last_desc = txq->size - 1;
+
+	/* Set maximum bandwidth for enabled TXQs */
+	mvreg_write(pp, MVETH_TXQ_TOKEN_CFG_REG(txq->id), 0x03ffffff);
+	mvreg_write(pp, MVETH_TXQ_TOKEN_COUNT_REG(txq->id), 0x3fffffff);
+
+	/* Set Tx descriptors queue starting address */
+	mvreg_write(pp, MVNETA_TXQ_BASE_ADDR_REG(txq->id), txq->descs_phys);
+	mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), txq->size);
+
+	txq->tx_skb = kmalloc(txq->size * sizeof(*txq->tx_skb), GFP_KERNEL);
+	if (txq->tx_skb == NULL) {
+		dma_free_coherent(pp->dev->dev.parent,
+				  txq->size * MVNETA_DESC_ALIGNED_SIZE,
+				  txq->descs, txq->descs_phys);
+		return -ENOMEM;
+	}
+	mvneta_tx_done_pkts_coal_set(pp, txq, txq->done_pkts_coal);
+
+	return 0;
+}
+
+/* Free allocated resources when mvneta_txq_init() fails to allocate memory*/
+static void mvneta_txq_deinit(struct mvneta_port *pp,
+			      struct mvneta_tx_queue *txq)
+{
+	kfree(txq->tx_skb);
+
+	if (txq->descs)
+		dma_free_coherent(pp->dev->dev.parent,
+				  txq->size * MVNETA_DESC_ALIGNED_SIZE,
+				  txq->descs, txq->descs_phys);
+
+	txq->descs             = NULL;
+	txq->last_desc         = 0;
+	txq->next_desc_to_proc = 0;
+	txq->descs_phys        = 0;
+
+	/* Set minimum bandwidth for disabled TXQs */
+	mvreg_write(pp, MVETH_TXQ_TOKEN_CFG_REG(txq->id), 0);
+	mvreg_write(pp, MVETH_TXQ_TOKEN_COUNT_REG(txq->id), 0);
+
+	/* Set Tx descriptors queue starting address and size */
+	mvreg_write(pp, MVNETA_TXQ_BASE_ADDR_REG(txq->id), 0);
+	mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), 0);
+}
+
+/* Cleanup all Tx queues */
+static void mvneta_cleanup_txqs(struct mvneta_port *pp)
+{
+	int queue;
+
+	for (queue = 0; queue < txq_number; queue++)
+		mvneta_txq_deinit(pp, &pp->txqs[queue]);
+}
+
+/* Cleanup all Rx queues */
+static void mvneta_cleanup_rxqs(struct mvneta_port *pp)
+{
+	int queue;
+
+	for (queue = 0; queue < rxq_number; queue++)
+		mvneta_rxq_deinit(pp, &pp->rxqs[queue]);
+}
+
+
+/* Init all Rx queues */
+static int mvneta_setup_rxqs(struct mvneta_port *pp)
+{
+	int queue;
+
+	for (queue = 0; queue < rxq_number; queue++) {
+		int err = mvneta_rxq_init(pp, &pp->rxqs[queue]);
+		if (err) {
+			netdev_err(pp->dev, "%s: can't create rxq=%d\n",
+				   __func__, queue);
+			mvneta_cleanup_rxqs(pp);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+/* Init all tx queues */
+static int mvneta_setup_txqs(struct mvneta_port *pp)
+{
+	int queue;
+
+	for (queue = 0; queue < txq_number; queue++) {
+		int err = mvneta_txq_init(pp, &pp->txqs[queue]);
+		if (err) {
+			netdev_err(pp->dev, "%s: can't create txq=%d\n",
+				   __func__, queue);
+			mvneta_cleanup_txqs(pp);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void mvneta_start_dev(struct mvneta_port *pp)
+{
+	mvneta_max_rx_size_set(pp, pp->pkt_size);
+	mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
+
+	/* start the Rx/Tx activity */
+	mvneta_port_enable(pp);
+
+	/* Enable polling on the port */
+	napi_enable(&pp->napi);
+
+	/* Unmask interrupts */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+		    MVNETA_RX_INTR_MASK(rxq_number));
+
+	phy_start(pp->phy_dev);
+	netif_tx_start_all_queues(pp->dev);
+}
+
+static void mvneta_stop_dev(struct mvneta_port *pp)
+{
+	phy_stop(pp->phy_dev);
+
+	napi_disable(&pp->napi);
+
+	netif_carrier_off(pp->dev);
+
+	mvneta_port_down(pp);
+	netif_tx_stop_all_queues(pp->dev);
+
+	/* Stop the port activity */
+	mvneta_port_disable(pp);
+
+	/* Clear all ethernet port interrupts */
+	mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
+	mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
+
+	/* Mask all ethernet port interrupts */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+
+	mvneta_tx_reset(pp);
+	mvneta_rx_reset(pp);
+}
+
+/* tx timeout callback - display a message and stop/start the network device */
+static void mvneta_tx_timeout(struct net_device *dev)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	netdev_info(dev, "tx timeout\n");
+	mvneta_stop_dev(pp);
+	mvneta_start_dev(pp);
+}
+
+/* Return positive if MTU is valid */
+static int mvneta_check_mtu_valid(struct net_device *dev, int mtu)
+{
+	if (mtu < 68) {
+		netdev_err(dev, "cannot change mtu to less than 68\n");
+		return -EINVAL;
+	}
+
+	/* 9676 == 9700 - 20 and rounding to 8 */
+	if (mtu > 9676) {
+		netdev_info(dev, "Illegal MTU value %d, round to 9676\n", mtu);
+		mtu = 9676;
+	}
+
+	if (!IS_ALIGNED(MVNETA_RX_PKT_SIZE(mtu), 8)) {
+		netdev_info(dev, "Illegal MTU value %d, rounding to %d\n",
+			mtu, ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8));
+		mtu = ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8);
+	}
+
+	return mtu;
+}
+
+/* Change the device mtu */
+static int mvneta_change_mtu(struct net_device *dev, int mtu)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+	int ret;
+
+	mtu = mvneta_check_mtu_valid(dev, mtu);
+	if (mtu < 0)
+		return -EINVAL;
+
+	dev->mtu = mtu;
+
+	if (!netif_running(dev))
+		return 0;
+
+	/* The interface is running, so we have to force a
+	 * reallocation of the RXQs
+	 */
+	mvneta_stop_dev(pp);
+
+	mvneta_cleanup_txqs(pp);
+	mvneta_cleanup_rxqs(pp);
+
+	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
+
+	ret = mvneta_setup_rxqs(pp);
+	if (ret) {
+		netdev_err(pp->dev, "unable to setup rxqs after MTU change\n");
+		return ret;
+	}
+
+	mvneta_setup_txqs(pp);
+
+	mvneta_start_dev(pp);
+	mvneta_port_up(pp);
+
+	return 0;
+}
+
+/* Handle setting mac address */
+static int mvneta_set_mac_addr(struct net_device *dev, void *addr)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+	u8 *mac = addr + 2;
+	int i;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	/* Remove previous address table entry */
+	mvneta_mac_addr_set(pp, dev->dev_addr, -1);
+
+	/* Set new addr in hw */
+	mvneta_mac_addr_set(pp, mac, rxq_def);
+
+	/* Set addr in the device */
+	for (i = 0; i < ETH_ALEN; i++)
+		dev->dev_addr[i] = mac[i];
+
+	return 0;
+}
+
+static void mvneta_adjust_link(struct net_device *ndev)
+{
+	struct mvneta_port *pp = netdev_priv(ndev);
+	struct phy_device *phydev = pp->phy_dev;
+	int status_change = 0;
+
+	if (phydev->link) {
+		if ((pp->speed != phydev->speed) ||
+		    (pp->duplex != phydev->duplex)) {
+			u32 val;
+
+			val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
+			val &= ~(MVNETA_GMAC_CONFIG_MII_SPEED |
+				 MVNETA_GMAC_CONFIG_GMII_SPEED |
+				 MVNETA_GMAC_CONFIG_FULL_DUPLEX);
+
+			if (phydev->duplex)
+				val |= MVNETA_GMAC_CONFIG_FULL_DUPLEX;
+
+			if (phydev->speed == SPEED_1000)
+				val |= MVNETA_GMAC_CONFIG_GMII_SPEED;
+			else
+				val |= MVNETA_GMAC_CONFIG_MII_SPEED;
+
+			mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
+
+			pp->duplex = phydev->duplex;
+			pp->speed  = phydev->speed;
+		}
+	}
+
+	if (phydev->link != pp->link) {
+		if (!phydev->link) {
+			pp->duplex = -1;
+			pp->speed = 0;
+		}
+
+		pp->link = phydev->link;
+		status_change = 1;
+	}
+
+	if (status_change) {
+		if (phydev->link) {
+			u32 val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
+			val |= (MVNETA_GMAC_FORCE_LINK_PASS |
+				MVNETA_GMAC_FORCE_LINK_DOWN);
+			mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
+			mvneta_port_up(pp);
+			netdev_info(pp->dev, "link up\n");
+		} else {
+			mvneta_port_down(pp);
+			netdev_info(pp->dev, "link down\n");
+		}
+	}
+}
+
+static int mvneta_mdio_probe(struct mvneta_port *pp)
+{
+	struct phy_device *phy_dev;
+
+	phy_dev = of_phy_connect(pp->dev, pp->phy_node, mvneta_adjust_link, 0,
+				 pp->phy_interface);
+	if (!phy_dev) {
+		netdev_err(pp->dev, "could not find the PHY\n");
+		return -ENODEV;
+	}
+
+	phy_dev->supported &= PHY_GBIT_FEATURES;
+	phy_dev->advertising = phy_dev->supported;
+
+	pp->phy_dev = phy_dev;
+	pp->link    = 0;
+	pp->duplex  = 0;
+	pp->speed   = 0;
+
+	return 0;
+}
+
+static void mvneta_mdio_remove(struct mvneta_port *pp)
+{
+	phy_disconnect(pp->phy_dev);
+	pp->phy_dev = NULL;
+}
+
+static int mvneta_open(struct net_device *dev)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+	int ret;
+
+	mvneta_mac_addr_set(pp, dev->dev_addr, rxq_def);
+
+	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
+
+	ret = mvneta_setup_rxqs(pp);
+	if (ret)
+		return ret;
+
+	ret = mvneta_setup_txqs(pp);
+	if (ret)
+		goto err_cleanup_rxqs;
+
+	/* Connect to port interrupt line */
+	ret = request_irq(pp->dev->irq, mvneta_isr, 0,
+			  MVNETA_DRIVER_NAME, pp);
+	if (ret) {
+		netdev_err(pp->dev, "cannot request irq %d\n", pp->dev->irq);
+		goto err_cleanup_txqs;
+	}
+
+	/* In default link is down */
+	netif_carrier_off(pp->dev);
+
+	ret = mvneta_mdio_probe(pp);
+	if (ret < 0) {
+		netdev_err(dev, "cannot probe MDIO bus\n");
+		goto err_free_irq;
+	}
+
+	mvneta_start_dev(pp);
+
+	return 0;
+
+err_free_irq:
+	free_irq(pp->dev->irq, pp);
+err_cleanup_txqs:
+	mvneta_cleanup_txqs(pp);
+err_cleanup_rxqs:
+	mvneta_cleanup_rxqs(pp);
+	return ret;
+}
+
+/* Stop the port, free port interrupt line */
+static int mvneta_stop(struct net_device *dev)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	mvneta_stop_dev(pp);
+	mvneta_mdio_remove(pp);
+	free_irq(dev->irq, pp);
+	mvneta_cleanup_rxqs(pp);
+	mvneta_cleanup_txqs(pp);
+	del_timer(&pp->tx_done_timer);
+	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
+
+	return 0;
+}
+
+/* Ethtool methods */
+
+/* Get settings (phy address, speed) for ethtools */
+int mvneta_ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (!pp->phy_dev)
+		return -ENODEV;
+
+	return phy_ethtool_gset(pp->phy_dev, cmd);
+}
+
+/* Set settings (phy address, speed) for ethtools */
+int mvneta_ethtool_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (!pp->phy_dev)
+		return -ENODEV;
+
+	return phy_ethtool_sset(pp->phy_dev, cmd);
+}
+
+/* Set interrupt coalescing for ethtools */
+static int mvneta_ethtool_set_coalesce(struct net_device *dev,
+				       struct ethtool_coalesce *c)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+	int queue;
+
+	for (queue = 0; queue < rxq_number; queue++) {
+		struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
+		rxq->time_coal = c->rx_coalesce_usecs;
+		rxq->pkts_coal = c->rx_max_coalesced_frames;
+		mvneta_rx_pkts_coal_set(pp, rxq, rxq->pkts_coal);
+		mvneta_rx_time_coal_set(pp, rxq, rxq->time_coal);
+	}
+
+	for (queue = 0; queue < txq_number; queue++) {
+		struct mvneta_tx_queue *txq = &pp->txqs[queue];
+		txq->done_pkts_coal = c->tx_max_coalesced_frames;
+		mvneta_tx_done_pkts_coal_set(pp, txq, txq->done_pkts_coal);
+	}
+
+	return 0;
+}
+
+/* get coalescing for ethtools */
+static int mvneta_ethtool_get_coalesce(struct net_device *dev,
+				       struct ethtool_coalesce *c)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	c->rx_coalesce_usecs        = pp->rxqs[0].time_coal;
+	c->rx_max_coalesced_frames  = pp->rxqs[0].pkts_coal;
+
+	c->tx_max_coalesced_frames =  pp->txqs[0].done_pkts_coal;
+	return 0;
+}
+
+
+static void mvneta_ethtool_get_drvinfo(struct net_device *dev,
+				    struct ethtool_drvinfo *drvinfo)
+{
+	strlcpy(drvinfo->driver, MVNETA_DRIVER_NAME,
+		sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, MVNETA_DRIVER_VERSION,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, dev_name(&dev->dev),
+		sizeof(drvinfo->bus_info));
+}
+
+
+static void mvneta_ethtool_get_ringparam(struct net_device *netdev,
+					 struct ethtool_ringparam *ring)
+{
+	struct mvneta_port *pp = netdev_priv(netdev);
+
+	ring->rx_max_pending = MVNETA_MAX_RXD;
+	ring->tx_max_pending = MVNETA_MAX_TXD;
+	ring->rx_pending = pp->rx_ring_size;
+	ring->tx_pending = pp->tx_ring_size;
+}
+
+static int mvneta_ethtool_set_ringparam(struct net_device *dev,
+					struct ethtool_ringparam *ring)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if ((ring->rx_pending == 0) || (ring->tx_pending == 0))
+		return -EINVAL;
+	pp->rx_ring_size = ring->rx_pending < MVNETA_MAX_RXD ?
+		ring->rx_pending : MVNETA_MAX_RXD;
+	pp->tx_ring_size = ring->tx_pending < MVNETA_MAX_TXD ?
+		ring->tx_pending : MVNETA_MAX_TXD;
+
+	if (netif_running(dev)) {
+		mvneta_stop(dev);
+		if (mvneta_open(dev)) {
+			netdev_err(dev,
+				   "error on opening device after ring param change\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct net_device_ops mvneta_netdev_ops = {
+	.ndo_open            = mvneta_open,
+	.ndo_stop            = mvneta_stop,
+	.ndo_start_xmit      = mvneta_tx,
+	.ndo_set_rx_mode     = mvneta_set_rx_mode,
+	.ndo_set_mac_address = mvneta_set_mac_addr,
+	.ndo_change_mtu      = mvneta_change_mtu,
+	.ndo_tx_timeout      = mvneta_tx_timeout,
+	.ndo_get_stats64     = mvneta_get_stats64,
+};
+
+const struct ethtool_ops mvneta_eth_tool_ops = {
+	.get_link       = ethtool_op_get_link,
+	.get_settings   = mvneta_ethtool_get_settings,
+	.set_settings   = mvneta_ethtool_set_settings,
+	.set_coalesce   = mvneta_ethtool_set_coalesce,
+	.get_coalesce   = mvneta_ethtool_get_coalesce,
+	.get_drvinfo    = mvneta_ethtool_get_drvinfo,
+	.get_ringparam  = mvneta_ethtool_get_ringparam,
+	.set_ringparam	= mvneta_ethtool_set_ringparam,
+};
+
+/* Initialize hw */
+static int __devinit mvneta_init(struct mvneta_port *pp, int phy_addr)
+{
+	int queue;
+
+	/* Disable port */
+	mvneta_port_disable(pp);
+
+	/* Set port default values */
+	mvneta_defaults_set(pp);
+
+	pp->txqs = kzalloc(txq_number * sizeof(struct mvneta_tx_queue),
+			   GFP_KERNEL);
+	if (!pp->txqs)
+		return -ENOMEM;
+
+	/* Initialize TX descriptor rings */
+	for (queue = 0; queue < txq_number; queue++) {
+		struct mvneta_tx_queue *txq = &pp->txqs[queue];
+		txq->id = queue;
+		txq->size = pp->tx_ring_size;
+		txq->done_pkts_coal = MVNETA_TXDONE_COAL_PKTS;
+	}
+
+	pp->rxqs = kzalloc(rxq_number * sizeof(struct mvneta_rx_queue),
+			   GFP_KERNEL);
+	if (!pp->rxqs) {
+		kfree(pp->txqs);
+		return -ENOMEM;
+	}
+
+	/* Create Rx descriptor rings */
+	for (queue = 0; queue < rxq_number; queue++) {
+		struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
+		rxq->id = queue;
+		rxq->size = pp->rx_ring_size;
+		rxq->pkts_coal = MVNETA_RX_COAL_PKTS;
+		rxq->time_coal = MVNETA_RX_COAL_USEC;
+	}
+
+	return 0;
+}
+
+static void mvneta_deinit(struct mvneta_port *pp)
+{
+	kfree(pp->txqs);
+	kfree(pp->rxqs);
+}
+
+/* platform glue : initialize decoding windows */
+static void __devinit
+mvneta_conf_mbus_windows(struct mvneta_port *pp,
+			 const struct mbus_dram_target_info *dram)
+{
+	u32 win_enable;
+	u32 win_protect;
+	int i;
+
+	for (i = 0; i < 6; i++) {
+		mvreg_write(pp, MVNETA_WIN_BASE(i), 0);
+		mvreg_write(pp, MVNETA_WIN_SIZE(i), 0);
+
+		if (i < 4)
+			mvreg_write(pp, MVNETA_WIN_REMAP(i), 0);
+	}
+
+	win_enable = 0x3f;
+	win_protect = 0;
+
+	for (i = 0; i < dram->num_cs; i++) {
+		const struct mbus_dram_window *cs = dram->cs + i;
+		mvreg_write(pp, MVNETA_WIN_BASE(i), (cs->base & 0xffff0000) |
+			    (cs->mbus_attr << 8) | dram->mbus_dram_target_id);
+
+		mvreg_write(pp, MVNETA_WIN_SIZE(i),
+			    (cs->size - 1) & 0xffff0000);
+
+		win_enable &= ~(1 << i);
+		win_protect |= 3 << (2 * i);
+	}
+
+	mvreg_write(pp, MVNETA_BASE_ADDR_ENABLE, win_enable);
+}
+
+/* Power up the port */
+static void __devinit mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
+{
+	u32 val;
+
+	/* MAC Cause register should be cleared */
+	mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
+
+	if (phy_mode == PHY_INTERFACE_MODE_SGMII)
+		mvneta_port_sgmii_config(pp);
+
+	mvneta_gmac_rgmii_set(pp, 1);
+
+	/* Cancel Port Reset */
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+	val &= ~MVNETA_GMAC2_PORT_RESET;
+	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+
+	while ((mvreg_read(pp, MVNETA_GMAC_CTRL_2) &
+		MVNETA_GMAC2_PORT_RESET) != 0)
+		continue;
+}
+
+/* Device initialization routine */
+static int __devinit mvneta_probe(struct platform_device *pdev)
+{
+	const struct mbus_dram_target_info *dram_target_info;
+	struct device_node *dn = pdev->dev.of_node;
+	struct device_node *phy_node;
+	u32 phy_addr;
+	struct mvneta_port *pp;
+	struct net_device *dev;
+	const char *mac_addr;
+	int phy_mode;
+	int err;
+
+	/* Our multiqueue support is not complete, so for now, only
+	 * allow the usage of the first RX queue
+	 */
+	if (rxq_def != 0) {
+		dev_err(&pdev->dev, "Invalid rxq_def argument: %d\n", rxq_def);
+		return -EINVAL;
+	}
+
+	dev = alloc_etherdev_mq(sizeof(struct mvneta_port), 8);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->irq = irq_of_parse_and_map(dn, 0);
+	if (dev->irq == 0) {
+		err = -EINVAL;
+		goto err_free_netdev;
+	}
+
+	phy_node = of_parse_phandle(dn, "phy", 0);
+	if (!phy_node) {
+		dev_err(&pdev->dev, "no associated PHY\n");
+		err = -ENODEV;
+		goto err_free_irq;
+	}
+
+	phy_mode = of_get_phy_mode(dn);
+	if (phy_mode < 0) {
+		dev_err(&pdev->dev, "incorrect phy-mode\n");
+		err = -EINVAL;
+		goto err_free_irq;
+	}
+
+	mac_addr = of_get_mac_address(dn);
+
+	if (!mac_addr || !is_valid_ether_addr(mac_addr))
+		eth_hw_addr_random(dev);
+	else
+		memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
+
+	dev->tx_queue_len = MVNETA_MAX_TXD;
+	dev->watchdog_timeo = 5 * HZ;
+	dev->netdev_ops = &mvneta_netdev_ops;
+
+	SET_ETHTOOL_OPS(dev, &mvneta_eth_tool_ops);
+
+	pp = netdev_priv(dev);
+
+	pp->tx_done_timer.function = mvneta_tx_done_timer_callback;
+	init_timer(&pp->tx_done_timer);
+	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
+
+	pp->weight = MVNETA_RX_POLL_WEIGHT;
+	pp->phy_node = phy_node;
+	pp->phy_interface = phy_mode;
+
+	pp->base = of_iomap(dn, 0);
+	if (pp->base == NULL) {
+		err = -ENOMEM;
+		goto err_free_irq;
+	}
+
+	pp->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(pp->clk)) {
+		err = PTR_ERR(pp->clk);
+		goto err_unmap;
+	}
+
+	clk_prepare_enable(pp->clk);
+
+	pp->tx_done_timer.data = (unsigned long)dev;
+
+	pp->tx_ring_size = MVNETA_MAX_TXD;
+	pp->rx_ring_size = MVNETA_MAX_RXD;
+
+	pp->dev = dev;
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
+	err = mvneta_init(pp, phy_addr);
+	if (err < 0) {
+		dev_err(&pdev->dev, "can't init eth hal\n");
+		goto err_clk;
+	}
+	mvneta_port_power_up(pp, phy_mode);
+
+	dram_target_info = mv_mbus_dram_info();
+	if (dram_target_info)
+		mvneta_conf_mbus_windows(pp, dram_target_info);
+
+	netif_napi_add(dev, &pp->napi, mvneta_poll, pp->weight);
+
+	err = register_netdev(dev);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to register\n");
+		goto err_deinit;
+	}
+
+	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM;
+	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM;
+	dev->priv_flags |= IFF_UNICAST_FLT;
+
+	netdev_info(dev, "mac: %pM\n", dev->dev_addr);
+
+	platform_set_drvdata(pdev, pp->dev);
+
+	return 0;
+
+err_deinit:
+	mvneta_deinit(pp);
+err_clk:
+	clk_disable_unprepare(pp->clk);
+err_unmap:
+	iounmap(pp->base);
+err_free_irq:
+	irq_dispose_mapping(dev->irq);
+err_free_netdev:
+	free_netdev(dev);
+	return err;
+}
+
+/* Device removal routine */
+static int __devexit mvneta_remove(struct platform_device *pdev)
+{
+	struct net_device  *dev = platform_get_drvdata(pdev);
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	unregister_netdev(dev);
+	mvneta_deinit(pp);
+	clk_disable_unprepare(pp->clk);
+	iounmap(pp->base);
+	irq_dispose_mapping(dev->irq);
+	free_netdev(dev);
+
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id mvneta_match[] = {
+	{ .compatible = "marvell,armada-370-neta" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mvneta_match);
+
+static struct platform_driver mvneta_driver = {
+	.probe = mvneta_probe,
+	.remove = __devexit_p(mvneta_remove),
+	.driver = {
+		.name = MVNETA_DRIVER_NAME,
+		.of_match_table = mvneta_match,
+	},
+};
+
+module_platform_driver(mvneta_driver);
+
+MODULE_DESCRIPTION("Marvell NETA Ethernet Driver - www.marvell.com");
+MODULE_AUTHOR("Rami Rosen <rosenr@marvell.com>, Thomas Petazzoni <thomas.petazzoni@free-electrons.com>");
+MODULE_LICENSE("GPL");
+
+module_param(rxq_number, int, S_IRUGO);
+module_param(txq_number, int, S_IRUGO);
+
+module_param(rxq_def, int, S_IRUGO);
+module_param(txq_def, int, S_IRUGO);
diff --git a/include/linux/clk/mvebu.h b/include/linux/clk/mvebu.h
new file mode 100644
index 0000000..8c4ae71
--- /dev/null
+++ b/include/linux/clk/mvebu.h
@@ -0,0 +1,22 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef __CLK_MVEBU_H_
+#define __CLK_MVEBU_H_
+
+void __init mvebu_clocks_init(void);
+
+#endif
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index 2ba1f7d..8ec18f6 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -10,15 +10,14 @@
 #include <linux/dmaengine.h>
 #include <linux/mbus.h>
 
-#define MV_XOR_SHARED_NAME	"mv_xor_shared"
-#define MV_XOR_NAME		"mv_xor"
+#define MV_XOR_NAME	"mv_xor"
 
-struct mv_xor_platform_data {
-	struct platform_device		*shared;
-	int				hw_id;
+struct mv_xor_channel_data {
 	dma_cap_mask_t			cap_mask;
-	size_t				pool_size;
 };
 
+struct mv_xor_platform_data {
+	struct mv_xor_channel_data    *channels;
+};
 
 #endif